diff --git a/ embedded_ml_exercise.qmd b/ embedded_ml_exercise.qmd
new file mode 100644
index 00000000..4d3673e3
--- /dev/null
+++ b/ embedded_ml_exercise.qmd	
@@ -0,0 +1,747 @@
+4 Embedded AI
+
+# Exercise - Image Classification
+
+### **Introduction**
+
+As we initiate our studies into embedded machine learning or tinyML,
+it\'s impossible to overlook the transformative impact of Computer
+Vision (CV) and Artificial Intelligence (AI) in our lives. These two
+intertwined disciplines redefine what machines can perceive and
+accomplish, from autonomous vehicles and robotics to healthcare and
+surveillance.
+
+More and more, we are facing an artificial intelligence (AI) revolution
+where, as stated by Gartner, **Edge AI** has a very high impact
+potential, and **it is for now**!
+
+![](images_4/media/image2.jpg){width="4.729166666666667in"
+height="4.895833333333333in"}
+
+In the \"bull-eye\" of emerging technologies, radar is the *Edge
+Computer Vision*, and when we talk about Machine Learning (ML) applied
+to vision, the first thing that comes to mind is **Image
+Classification**, a kind of ML \"Hello World\"!
+
+This exercise will explore a computer vision project utilizing
+Convolutional Neural Networks (CNNs) for real-time image classification.
+Leveraging TensorFlow\'s robust ecosystem, we\'ll implement a
+pre-trained MobileNet model and adapt it for edge deployment. The focus
+will be optimizing the model to run efficiently on resource-constrained
+hardware without sacrificing accuracy.
+
+We\'ll employ techniques like quantization and pruning to reduce the
+computational load. By the end of this tutorial, you\'ll have a working
+prototype capable of classifying images in real time, all running on a
+low-power embedded system based on the Arduino Nicla Vision board.
+
+### **Computer Vision**
+
+At its core, computer vision aims to enable machines to interpret and
+make decisions based on visual data from the world---essentially
+mimicking the capability of the human optical system. Conversely, AI is
+a broader field encompassing machine learning, natural language
+processing, and robotics, among other technologies. When you bring AI
+algorithms into computer vision projects, you supercharge the system\'s
+ability to understand, interpret, and react to visual stimuli.
+
+When discussing Computer Vision projects applied to embedded devices,
+the most common applications that come to mind are *Image
+Classification* and *Object Detection*.
+
+![image.png](images_4/media/image15.jpg){width="6.5in"
+height="2.8333333333333335in"}
+
+Both models can be implemented on tiny devices like the Arduino Nicla
+Vision and used on real projects. Let\'s start with the first one.
+
+### **Image Classification Project**
+
+The first step in any ML project is to define our goal. In this case, it
+is to detect and classify two specific objects present in one image. For
+this project, we will use two small toys: a *robot* and a small
+Brazilian parrot (named *Periquito*). Also, we will collect images of a
+*background* where those two objects are absent.
+
+![image.png](images_4/media/image36.jpg){width="6.5in"
+height="3.638888888888889in"}
+
+### **Data Collection**
+
+Once you have defined your Machine Learning project goal, the next and
+most crucial step is the dataset collection. You can use the Edge
+Impulse Studio, the OpenMV IDE we installed, or even your phone for the
+image capture. Here, we will use the OpenMV IDE for that.
+
+**Collecting Dataset with OpenMV IDE**
+
+First, create in your computer a folder where your data will be saved,
+for example, \"data.\" Next, on the OpenMV IDE, go to Tools \> Dataset
+Editor and select New Dataset to start the dataset collection:
+
+![image.png](images_4/media/image29.png){width="6.291666666666667in"
+height="4.010416666666667in"}
+
+The IDE will ask you to open the file where your data will be saved and
+choose the \"data\" folder that was created. Note that new icons will
+appear on the Left panel.
+
+![image.png](images_4/media/image46.png){width="0.9583333333333334in"
+height="1.5208333333333333in"}
+
+Using the upper icon (1), enter with the first class name, for example,
+\"periquito\":
+
+![image.png](images_4/media/image22.png){width="3.25in"
+height="2.65625in"}
+
+Run the dataset_capture_script.py, and clicking on the bottom icon (2),
+will start capturing images:
+
+![image.png](images_4/media/image43.png){width="6.5in"
+height="4.041666666666667in"}
+
+Repeat the same procedure with the other classes
+
+![image.png](images_4/media/image6.jpg){width="6.5in"
+height="3.0972222222222223in"}
+
+> *We suggest around 60 images from each category. Try to capture
+> different angles, backgrounds, and light conditions.*
+
+The stored images use a QVGA frame size 320x240 and RGB565 (color pixel
+format).
+
+After capturing your dataset, close the Dataset Editor Tool on the Tools
+\> Dataset Editor.
+
+On your computer, you will end with a dataset that contains three
+classes: periquito, robot, and background.
+
+![image.png](images_4/media/image20.png){width="6.5in"
+height="2.2083333333333335in"}
+
+You should return to Edge Impulse Studio and upload the dataset to your
+project.
+
+### **Training the model with Edge Impulse Studio**
+
+We will use the Edge Impulse Studio for training our model. Enter your
+account credentials at Edge Impulse and create a new project:
+
+![image.png](images_4/media/image45.png){width="6.5in"
+height="4.263888888888889in"}
+
+> *Here, you can clone a similar project:*
+> *[NICLA-Vision_Image_Classification](https://studio.edgeimpulse.com/public/273858/latest).*
+
+### **Dataset**
+
+Using the EI Studio (or *Studio*), we will pass over four main steps to
+have our model ready for use on the Nicla Vision board: Dataset,
+Impulse, Tests, and Deploy (on the Edge Device, in this case, the
+NiclaV).
+
+![image.png](images_4/media/image41.jpg){width="6.5in"
+height="4.194444444444445in"}
+
+Regarding the Dataset, it is essential to point out that our Original
+Dataset, captured with the OpenMV IDE, will be split into three parts:
+Training, Validation, and Test. The Test Set will be divided from the
+beginning and left a part to be used only in the Test phase after
+training. The Validation Set will be used during training.
+
+![image.png](images_4/media/image7.jpg){width="6.5in"
+height="4.763888888888889in"}
+
+On Studio, go to the Data acquisition tab, and on the UPLOAD DATA
+section, upload from your computer the files from chosen categories:
+
+![image.png](images_4/media/image39.png){width="6.5in"
+height="4.263888888888889in"}
+
+Left to the Studio to automatically split the original dataset into
+training and test and choose the label related to that specific data:
+
+![image.png](images_4/media/image30.png){width="6.5in"
+height="4.263888888888889in"}
+
+Repeat the procedure for all three classes. At the end, you should see
+your \"raw data in the Studio:
+
+![image.png](images_4/media/image11.png){width="6.5in"
+height="4.263888888888889in"}
+
+The Studio allows you to explore your data, showing a complete view of
+all the data in your project. You can clear, inspect, or change labels
+by clicking on individual data items. In our case, a simple project, the
+data seems OK.
+
+![image.png](images_4/media/image44.png){width="6.5in"
+height="4.263888888888889in"}
+
+### **The Impulse Design**
+
+In this phase, we should define how to:
+
+-   Pre-process our data, which consists of resizing the individual
+    > images and determining the color depth to use (RGB or Grayscale)
+    > and
+
+-   Design a Model that will be \"Transfer Learning (Images)\" to
+    > fine-tune a pre-trained MobileNet V2 image classification model on
+    > our data. This method performs well even with relatively small
+    > image datasets (around 150 images in our case).
+
+![image.png](images_4/media/image23.jpg){width="6.5in"
+height="4.0in"}
+
+Transfer Learning with MobileNet offers a streamlined approach to model
+training, which is especially beneficial for resource-constrained
+environments and projects with limited labeled data. MobileNet, known
+for its lightweight architecture, is a pre-trained model that has
+already learned valuable features from a large dataset (ImageNet).
+
+![image.png](images_4/media/image9.jpg){width="6.5in"
+height="1.9305555555555556in"}
+
+By leveraging these learned features, you can train a new model for your
+specific task with fewer data and computational resources yet achieve
+competitive accuracy.
+
+![image.png](images_4/media/image32.jpg){width="6.5in"
+height="2.3055555555555554in"}
+
+This approach significantly reduces training time and computational
+cost, making it ideal for quick prototyping and deployment on embedded
+devices where efficiency is paramount.
+
+Go to the Impulse Design Tab and create the *impulse*, defining an image
+size of 96x96 and squashing them (squared form, without crop). Select
+Image and Transfer Learning blocks. Save the Impulse.
+
+![image.png](images_4/media/image16.png){width="6.5in"
+height="4.263888888888889in"}
+
+### **Image Pre-Processing**
+
+All input QVGA/RGB565 images will be converted to 27,640 features
+(96x96x3).
+
+![image.png](images_4/media/image17.png){width="6.5in"
+height="4.319444444444445in"}
+
+Press \[Save parameters\] and Generate all features:
+
+![image.png](images_4/media/image5.png){width="6.5in"
+height="4.263888888888889in"}
+
+### **Model Design**
+
+In 2007, Google introduced
+[[MobileNetV1]{.underline}](https://research.googleblog.com/2017/06/mobilenets-open-source-models-for.html),
+a family of general-purpose computer vision neural networks designed
+with mobile devices in mind to support classification, detection, and
+more. MobileNets are small, low-latency, low-power models parameterized
+to meet the resource constraints of various use cases. in 2018, Google
+launched [MobileNetV2: Inverted Residuals and Linear
+Bottlenecks](https://arxiv.org/abs/1801.04381).
+
+MobileNet V1 and MobileNet V2 aim for mobile efficiency and embedded
+vision applications but differ in architectural complexity and
+performance. While both use depthwise separable convolutions to reduce
+the computational cost, MobileNet V2 introduces Inverted Residual Blocks
+and Linear Bottlenecks to enhance performance. These new features allow
+V2 to capture more complex features using fewer parameters, making it
+computationally more efficient and generally more accurate than its
+predecessor. Additionally, V2 employs a non-linear activation in the
+intermediate expansion layer. Still, it uses a linear activation for the
+bottleneck layer, a design choice found to preserve important
+information through the network better. MobileNet V2 offers a more
+optimized architecture for higher accuracy and efficiency and will be
+used in this project.
+
+Although the base MobileNet architecture is already tiny and has low
+latency, many times, a specific use case or application may require the
+model to be smaller and faster. MobileNets introduces a straightforward
+parameter α (alpha) called width multiplier to construct these smaller,
+less computationally expensive models. The role of the width multiplier
+α is to thin a network uniformly at each layer.
+
+Edge Impulse Studio has available MobileNetV1 (96x96 images) and V2
+(96x96 and 160x160 images), with several different **α** values (from
+0.05 to 1.0). For example, you will get the highest accuracy with V2,
+160x160 images, and α=1.0. Of course, there is a trade-off. The higher
+the accuracy, the more memory (around 1.3M RAM and 2.6M ROM) will be
+needed to run the model, implying more latency. The smaller footprint
+will be obtained at another extreme with MobileNetV1 and α=0.10 (around
+53.2K RAM and 101K ROM).
+
+![image.png](images_4/media/image27.jpg){width="6.5in"
+height="3.5277777777777777in"}
+
+For this project, we will use **MobileNetV2 96x96 0.1**, which estimates
+a memory cost of 265.3 KB in RAM. This model should be OK for the Nicla
+Vision with 1MB of SRAM. On the Transfer Learning Tab, select this
+model:
+
+![image.png](images_4/media/image24.png){width="6.5in"
+height="4.263888888888889in"}
+
+Another necessary technique to be used with Deep Learning is **Data
+Augmentation**. Data augmentation is a method that can help improve the
+accuracy of machine learning models, creating additional artificial
+data. A data augmentation system makes small, random changes to your
+training data during the training process (such as flipping, cropping,
+or rotating the images).
+
+Under the rood, here you can see how Edge Impulse implements a data
+Augmentation policy on your data:
+
+  -----------------------------------------------------------------------
+  \# Implements the data augmentation policy\
+  def augment_image(image, label):\
+  \# Flips the image randomly\
+  image = tf.image.random_flip_left_right(image)\
+  \
+  \# Increase the image size, then randomly crop it down to\
+  \# the original dimensions\
+  resize_factor = random.uniform(1, 1.2)\
+  new_height = math.floor(resize_factor \* INPUT_SHAPE\[0\])\
+  new_width = math.floor(resize_factor \* INPUT_SHAPE\[1\])\
+  image = tf.image.resize_with_crop_or_pad(image, new_height, new_width)\
+  image = tf.image.random_crop(image, size=INPUT_SHAPE)\
+  \
+  \# Vary the brightness of the image\
+  image = tf.image.random_brightness(image, max_delta=0.2)\
+  \
+  return image, label
+  -----------------------------------------------------------------------
+
+  -----------------------------------------------------------------------
+
+Exposure to these variations during training can help prevent your model
+from taking shortcuts by \"memorizing\" superficial clues in your
+training data, meaning it may better reflect the deep underlying
+patterns in your dataset.
+
+The final layer of our model will have 12 neurons with a 15% dropout for
+overfitting prevention. Here is the Training result:
+
+![image.png](images_4/media/image31.jpg){width="6.5in"
+height="3.5in"}
+
+The result is excellent, with 77ms of latency, which should result in
+13fps (frames per second) during inference.
+
+### **Model Testing**
+
+![image.png](images_4/media/image10.jpg){width="6.5in"
+height="3.8472222222222223in"}
+
+Now, you should take the data put apart at the start of the project and
+run the trained model having them as input:
+
+![image.png](images_4/media/image34.png){width="3.1041666666666665in"
+height="1.7083333333333333in"}
+
+The result was, again, excellent.
+
+![image.png](images_4/media/image12.png){width="6.5in"
+height="4.263888888888889in"}
+
+### **Deploying the model**
+
+At this point, we can deploy the trained model as.tflite and use the
+OpenMV IDE to run it using MicroPython, or we can deploy it as a C/C++
+or an Arduino library.
+
+![image.png](images_4/media/image28.jpg){width="6.5in"
+height="3.763888888888889in"}
+
+**Arduino Library**
+
+First, Let\'s deploy it as an Arduino Library:
+
+![image.png](images_4/media/image48.png){width="6.5in"
+height="4.263888888888889in"}
+
+You should install the library as.zip on the Arduino IDE and run the
+sketch nicla_vision_camera.ino available in Examples under your library
+name.
+
+> *Note that Arduino Nicla Vision has, by default, 512KB of RAM
+> allocated for the M7 core and an additional 244KB on the M4 address
+> space. In the code, this allocation was changed to 288 kB to guarantee
+> that the model will run on the device
+> (malloc_addblock((void\*)0x30000000, 288 \* 1024);).*
+
+The result was good, with 86ms of measured latency.
+
+![image.png](images_4/media/image25.jpg){width="6.5in"
+height="3.4444444444444446in"}
+
+Here is a short video showing the inference results:
+[[https://youtu.be/bZPZZJblU-o]{.underline}](https://youtu.be/bZPZZJblU-o)
+
+**OpenMV**
+
+It is possible to deploy the trained model to be used with OpenMV in two
+ways: as a library and as a firmware.
+
+Three files are generated as a library: the.tflite model, a list with
+the labels, and a simple MicroPython script that can make inferences
+using the model.
+
+![image.png](images_4/media/image26.png){width="6.5in"
+height="1.0in"}
+
+Running this model as a.tflite directly in the Nicla was impossible. So,
+we can sacrifice the accuracy using a smaller model or deploy the model
+as an OpenMV Firmware (FW). As an FW, the Edge Impulse Studio generates
+optimized models, libraries, and frameworks needed to make the
+inference. Let\'s explore this last one.
+
+Select OpenMV Firmware on the Deploy Tab and press \[Build\].
+
+![image.png](images_4/media/image3.png){width="6.5in"
+height="4.263888888888889in"}
+
+On your computer, you will find a ZIP file. Open it:
+
+![Pasted Graphic
+64.png](images_4/media/image33.png){width="6.5in"
+height="2.625in"}
+
+Use the Bootloader tool on the OpenMV IDE to load the FW on your board:
+
+![Pasted Graphic
+63.png](images_4/media/image35.jpg){width="6.5in"
+height="3.625in"}
+
+Select the appropriate file (.bin for Nicla-Vision):
+
+![Pasted Graphic
+65.png](images_4/media/image8.png){width="6.5in"
+height="1.9722222222222223in"}
+
+After the download is finished, press OK:
+
+![DFU firmware update
+complete!.png](images_4/media/image40.png){width="3.875in"
+height="5.708333333333333in"}
+
+If a message says that the FW is outdated, DO NOT UPGRADE. Select
+\[NO\].
+
+![image.png](images_4/media/image42.png){width="4.572916666666667in"
+height="2.875in"}
+
+Now, open the script **ei_image_classification.py** that was downloaded
+from the Studio and the.bin file for the Nicla.
+
+![image.png](images_4/media/image14.png){width="6.5in"
+height="4.0in"}
+
+And run it. Pointing the camera to the objects we want to classify, the
+inference result will be displayed on the Serial Terminal.
+
+![image.png](images_4/media/image37.png){width="6.5in"
+height="3.736111111111111in"}
+
+**Changing Code to add labels:**
+
+The code provided by Edge Impulse can be modified so that we can see,
+for test reasons, the inference result directly on the image displayed
+on the OpenMV IDE.
+
+[[Upload the code from
+GitHub,]{.underline}](https://github.com/Mjrovai/Arduino_Nicla_Vision/blob/main/Micropython/nicla_image_classification.py)
+or modify it as below:
+
+  -----------------------------------------------------------------------
+  \# Marcelo Rovai - NICLA Vision - Image Classification\
+  \# Adapted from Edge Impulse - OpenMV Image Classification Example\
+  \# \@24Aug23\
+  \
+  import sensor, image, time, os, tf, uos, gc\
+  \
+  sensor.reset() \# Reset and initialize the sensor.\
+  sensor.set_pixformat(sensor.RGB565) \# Set pxl fmt to RGB565 (or
+  GRAYSCALE)\
+  sensor.set_framesize(sensor.QVGA) \# Set frame size to QVGA (320x240)\
+  sensor.set_windowing((240, 240)) \# Set 240x240 window.\
+  sensor.skip_frames(time=2000) \# Let the camera adjust.\
+  \
+  net = None\
+  labels = None\
+  \
+  try:\
+  \# Load built in model\
+  labels, net = tf.load_builtin_model(\'trained\')\
+  except Exception as e:\
+  raise Exception(e)\
+  \
+  clock = time.clock()\
+  while(True):\
+  clock.tick() \# Starts tracking elapsed time.\
+  \
+  img = sensor.snapshot()\
+  \
+  \# default settings just do one detection\
+  for obj in net.classify(img,\
+  min_scale=1.0,\
+  scale_mul=0.8,\
+  x_overlap=0.5,\
+  y_overlap=0.5):\
+  fps = clock.fps()\
+  lat = clock.avg()\
+  \
+  print(\"\*\*\*\*\*\*\*\*\*\*\\nPrediction:\")\
+  img.draw_rectangle(obj.rect())\
+  \# This combines the labels and confidence values into a list of
+  tuples\
+  predictions_list = list(zip(labels, obj.output()))\
+  \
+  max_val = predictions_list\[0\]\[1\]\
+  max_lbl = \'background\'\
+  for i in range(len(predictions_list)):\
+  val = predictions_list\[i\]\[1\]\
+  lbl = predictions_list\[i\]\[0\]\
+  \
+  if val \> max_val:\
+  max_val = val\
+  max_lbl = lbl\
+  \
+  \# Print label with the highest probability\
+  if max_val \< 0.5:\
+  max_lbl = \'uncertain\'\
+  print(\"{} with a prob of {:.2f}\".format(max_lbl, max_val))\
+  print(\"FPS: {:.2f} fps ==\> latency: {:.0f} ms\".format(fps, lat))\
+  \
+  \# Draw label with highest probability to image viewer\
+  img.draw_string(\
+  10, 10,\
+  max_lbl + \"\\n{:.2f}\".format(max_val),\
+  mono_space = False,\
+  scale=2\
+  )
+  -----------------------------------------------------------------------
+
+  -----------------------------------------------------------------------
+
+Here you can see the result:
+
+![image.png](images_4/media/image47.jpg){width="6.5in"
+height="2.9444444444444446in"}
+
+Note that the latency (136 ms) is almost double what we got directly
+with the Arduino IDE. This is because we are using the IDE as an
+interface and the time to wait for the camera to be ready. If we start
+the clock just before the inference:
+
+![image.png](images_4/media/image13.jpg){width="6.5in"
+height="2.0972222222222223in"}
+
+The latency will drop to only 71 ms.
+
+![image.png](images_4/media/image1.jpg){width="3.5520833333333335in"
+height="1.53125in"}
+
+### ***OpenMV Cam runs about half as fast when connected to the IDE. The FPS should increase once disconnected.***
+
+### **Post-Processing with LEDs**
+
+When working with embedded machine learning, we are looking for devices
+that can continually proceed with the inference and result, taking some
+action directly on the physical world and not displaying the result on a
+connected computer. To simulate this, we will define one LED to light up
+for each one of the possible inference results.
+
+![image.png](images_4/media/image38.jpg){width="6.5in"
+height="3.236111111111111in"}
+
+For that, we should [[upload the code from
+GitHub]{.underline}](https://github.com/Mjrovai/Arduino_Nicla_Vision/blob/main/Micropython/nicla_image_classification_LED.py)
+or change the last code to include the LEDs:
+
+  -----------------------------------------------------------------------
+  \# Marcelo Rovai - NICLA Vision - Image Classification with LEDs\
+  \# Adapted from Edge Impulse - OpenMV Image Classification Example\
+  \# \@24Aug23\
+  \
+  import sensor, image, time, os, tf, uos, gc, pyb\
+  \
+  ledRed = pyb.LED(1)\
+  ledGre = pyb.LED(2)\
+  ledBlu = pyb.LED(3)\
+  \
+  sensor.reset() \# Reset and initialize the sensor.\
+  sensor.set_pixformat(sensor.RGB565) \# Set pixl fmt to RGB565 (or
+  GRAYSCALE)\
+  sensor.set_framesize(sensor.QVGA) \# Set frame size to QVGA (320x240)\
+  sensor.set_windowing((240, 240)) \# Set 240x240 window.\
+  sensor.skip_frames(time=2000) \# Let the camera adjust.\
+  \
+  net = None\
+  labels = None\
+  \
+  ledRed.off()\
+  ledGre.off()\
+  ledBlu.off()\
+  \
+  try:\
+  \# Load built in model\
+  labels, net = tf.load_builtin_model(\'trained\')\
+  except Exception as e:\
+  raise Exception(e)\
+  \
+  clock = time.clock()\
+  \
+  \
+  def setLEDs(max_lbl):\
+  \
+  if max_lbl == \'uncertain\':\
+  ledRed.on()\
+  ledGre.off()\
+  ledBlu.off()\
+  \
+  if max_lbl == \'periquito\':\
+  ledRed.off()\
+  ledGre.on()\
+  ledBlu.off()\
+  \
+  if max_lbl == \'robot\':\
+  ledRed.off()\
+  ledGre.off()\
+  ledBlu.on()\
+  \
+  if max_lbl == \'background\':\
+  ledRed.off()\
+  ledGre.off()\
+  ledBlu.off()\
+  \
+  \
+  while(True):\
+  img = sensor.snapshot()\
+  clock.tick() \# Starts tracking elapsed time.\
+  \
+  \# default settings just do one detection.\
+  for obj in net.classify(img,\
+  min_scale=1.0,\
+  scale_mul=0.8,\
+  x_overlap=0.5,\
+  y_overlap=0.5):\
+  fps = clock.fps()\
+  lat = clock.avg()\
+  \
+  print(\"\*\*\*\*\*\*\*\*\*\*\\nPrediction:\")\
+  img.draw_rectangle(obj.rect())\
+  \# This combines the labels and confidence values into a list of
+  tuples\
+  predictions_list = list(zip(labels, obj.output()))\
+  \
+  max_val = predictions_list\[0\]\[1\]\
+  max_lbl = \'background\'\
+  for i in range(len(predictions_list)):\
+  val = predictions_list\[i\]\[1\]\
+  lbl = predictions_list\[i\]\[0\]\
+  \
+  if val \> max_val:\
+  max_val = val\
+  max_lbl = lbl\
+  \
+  \# Print label and turn on LED with the highest probability\
+  if max_val \< 0.8:\
+  max_lbl = \'uncertain\'\
+  \
+  setLEDs(max_lbl)\
+  \
+  print(\"{} with a prob of {:.2f}\".format(max_lbl, max_val))\
+  print(\"FPS: {:.2f} fps ==\> latency: {:.0f} ms\".format(fps, lat))\
+  \
+  \# Draw label with highest probability to image viewer\
+  img.draw_string(\
+  10, 10,\
+  max_lbl + \"\\n{:.2f}\".format(max_val),\
+  mono_space = False,\
+  scale=2\
+  )
+  -----------------------------------------------------------------------
+
+  -----------------------------------------------------------------------
+
+Now, each time that a class gets a result superior of 0.8, the
+correspondent LED will be light on as below:
+
+-   Led Red 0n: Uncertain (no one class is over 0.8)
+
+-   Led Green 0n: Periquito \> 0.8
+
+-   Led Blue 0n: Robot \> 0.8
+
+-   All LEDs Off: Background \> 0.8
+
+Here is the result:
+
+![image.png](images_4/media/image18.jpg){width="6.5in"
+height="3.6527777777777777in"}
+
+In more detail
+
+![image.png](images_4/media/image21.jpg){width="6.5in"
+height="2.0972222222222223in"}
+
+### **Image Classification (non-official) Benchmark**
+
+Several development boards can be used for embedded machine learning
+(tinyML), and the most common ones for Computer Vision applications
+(with low energy), are the ESP32 CAM, the Seeed XIAO ESP32S3 Sense, the
+Arduinos Nicla Vison, and Portenta.
+
+![image.png](images_4/media/image19.jpg){width="6.5in"
+height="4.194444444444445in"}
+
+Using the opportunity, the same trained model was deployed on the
+ESP-CAM, the XIAO, and Portenta (in this one, the model was trained
+again, using grayscaled images to be compatible with its camera. Here is
+the result, deploying the models as Arduino\'s Library:
+
+![image.png](images_4/media/image4.jpg){width="6.5in"
+height="3.4444444444444446in"}
+
+### **Conclusion**
+
+Before we finish, consider that Computer Vision is more than just image
+classification. For example, you can develop Edge Machine Learning
+projects around vision in several areas, such as:
+
+-   **Autonomous Vehicles**: Use sensor fusion, lidar data, and computer
+    > vision algorithms to navigate and make decisions.
+
+-   **Healthcare**: Automated diagnosis of diseases through MRI, X-ray,
+    > and CT scan image analysis
+
+-   **Retail**: Automated checkout systems that identify products as
+    > they pass through a scanner.
+
+-   **Security and Surveillance**: Facial recognition, anomaly
+    > detection, and object tracking in real-time video feeds.
+
+-   **Augmented Reality**: Object detection and classification to
+    > overlay digital information in the real world.
+
+-   **Industrial Automation**: Visual inspection of products, predictive
+    > maintenance, and robot and drone guidance.
+
+-   **Agriculture**: Drone-based crop monitoring and automated
+    > harvesting.
+
+-   **Natural Language Processing**: Image captioning and visual
+    > question answering.
+
+-   **Gesture Recognition**: For gaming, sign language translation, and
+    > human-machine interaction.
+
+-   **Content Recommendation**: Image-based recommendation systems in
+    > e-commerce.
diff --git a/images_4/media/image1.jpg b/images_4/media/image1.jpg
new file mode 100644
index 00000000..48985805
Binary files /dev/null and b/images_4/media/image1.jpg differ
diff --git a/images_4/media/image10.jpg b/images_4/media/image10.jpg
new file mode 100644
index 00000000..8cf6eb84
Binary files /dev/null and b/images_4/media/image10.jpg differ
diff --git a/images_4/media/image11.png b/images_4/media/image11.png
new file mode 100644
index 00000000..613f3581
Binary files /dev/null and b/images_4/media/image11.png differ
diff --git a/images_4/media/image12.png b/images_4/media/image12.png
new file mode 100644
index 00000000..24d869c4
Binary files /dev/null and b/images_4/media/image12.png differ
diff --git a/images_4/media/image13.jpg b/images_4/media/image13.jpg
new file mode 100644
index 00000000..5298efc0
Binary files /dev/null and b/images_4/media/image13.jpg differ
diff --git a/images_4/media/image14.png b/images_4/media/image14.png
new file mode 100644
index 00000000..d8702a68
Binary files /dev/null and b/images_4/media/image14.png differ
diff --git a/images_4/media/image15.jpg b/images_4/media/image15.jpg
new file mode 100644
index 00000000..5aea170d
Binary files /dev/null and b/images_4/media/image15.jpg differ
diff --git a/images_4/media/image16.png b/images_4/media/image16.png
new file mode 100644
index 00000000..af218e99
Binary files /dev/null and b/images_4/media/image16.png differ
diff --git a/images_4/media/image17.png b/images_4/media/image17.png
new file mode 100644
index 00000000..8fc0973d
Binary files /dev/null and b/images_4/media/image17.png differ
diff --git a/images_4/media/image18.jpg b/images_4/media/image18.jpg
new file mode 100644
index 00000000..38d81100
Binary files /dev/null and b/images_4/media/image18.jpg differ
diff --git a/images_4/media/image19.jpg b/images_4/media/image19.jpg
new file mode 100644
index 00000000..c60501e6
Binary files /dev/null and b/images_4/media/image19.jpg differ
diff --git a/images_4/media/image2.jpg b/images_4/media/image2.jpg
new file mode 100644
index 00000000..f5c2e439
Binary files /dev/null and b/images_4/media/image2.jpg differ
diff --git a/images_4/media/image20.png b/images_4/media/image20.png
new file mode 100644
index 00000000..dd254917
Binary files /dev/null and b/images_4/media/image20.png differ
diff --git a/images_4/media/image21.jpg b/images_4/media/image21.jpg
new file mode 100644
index 00000000..b552ec21
Binary files /dev/null and b/images_4/media/image21.jpg differ
diff --git a/images_4/media/image22.png b/images_4/media/image22.png
new file mode 100644
index 00000000..71987ffd
Binary files /dev/null and b/images_4/media/image22.png differ
diff --git a/images_4/media/image23.jpg b/images_4/media/image23.jpg
new file mode 100644
index 00000000..48bcaef2
Binary files /dev/null and b/images_4/media/image23.jpg differ
diff --git a/images_4/media/image24.png b/images_4/media/image24.png
new file mode 100644
index 00000000..918d3a66
Binary files /dev/null and b/images_4/media/image24.png differ
diff --git a/images_4/media/image25.jpg b/images_4/media/image25.jpg
new file mode 100644
index 00000000..f4cf0e5d
Binary files /dev/null and b/images_4/media/image25.jpg differ
diff --git a/images_4/media/image26.png b/images_4/media/image26.png
new file mode 100644
index 00000000..e6752d55
Binary files /dev/null and b/images_4/media/image26.png differ
diff --git a/images_4/media/image27.jpg b/images_4/media/image27.jpg
new file mode 100644
index 00000000..bc2635d3
Binary files /dev/null and b/images_4/media/image27.jpg differ
diff --git a/images_4/media/image28.jpg b/images_4/media/image28.jpg
new file mode 100644
index 00000000..b857f18f
Binary files /dev/null and b/images_4/media/image28.jpg differ
diff --git a/images_4/media/image29.png b/images_4/media/image29.png
new file mode 100644
index 00000000..272a0fe8
Binary files /dev/null and b/images_4/media/image29.png differ
diff --git a/images_4/media/image3.png b/images_4/media/image3.png
new file mode 100644
index 00000000..bdc1b381
Binary files /dev/null and b/images_4/media/image3.png differ
diff --git a/images_4/media/image30.png b/images_4/media/image30.png
new file mode 100644
index 00000000..92857046
Binary files /dev/null and b/images_4/media/image30.png differ
diff --git a/images_4/media/image31.jpg b/images_4/media/image31.jpg
new file mode 100644
index 00000000..7b4d60bd
Binary files /dev/null and b/images_4/media/image31.jpg differ
diff --git a/images_4/media/image32.jpg b/images_4/media/image32.jpg
new file mode 100644
index 00000000..b3764526
Binary files /dev/null and b/images_4/media/image32.jpg differ
diff --git a/images_4/media/image33.png b/images_4/media/image33.png
new file mode 100644
index 00000000..e6549013
Binary files /dev/null and b/images_4/media/image33.png differ
diff --git a/images_4/media/image34.png b/images_4/media/image34.png
new file mode 100644
index 00000000..28f85e7d
Binary files /dev/null and b/images_4/media/image34.png differ
diff --git a/images_4/media/image35.jpg b/images_4/media/image35.jpg
new file mode 100644
index 00000000..9797154d
Binary files /dev/null and b/images_4/media/image35.jpg differ
diff --git a/images_4/media/image36.jpg b/images_4/media/image36.jpg
new file mode 100644
index 00000000..5bfffd04
Binary files /dev/null and b/images_4/media/image36.jpg differ
diff --git a/images_4/media/image37.png b/images_4/media/image37.png
new file mode 100644
index 00000000..a91610b7
Binary files /dev/null and b/images_4/media/image37.png differ
diff --git a/images_4/media/image38.jpg b/images_4/media/image38.jpg
new file mode 100644
index 00000000..1c5e92a8
Binary files /dev/null and b/images_4/media/image38.jpg differ
diff --git a/images_4/media/image39.png b/images_4/media/image39.png
new file mode 100644
index 00000000..2c908993
Binary files /dev/null and b/images_4/media/image39.png differ
diff --git a/images_4/media/image4.jpg b/images_4/media/image4.jpg
new file mode 100644
index 00000000..2a0f5dfc
Binary files /dev/null and b/images_4/media/image4.jpg differ
diff --git a/images_4/media/image40.png b/images_4/media/image40.png
new file mode 100644
index 00000000..28100ac2
Binary files /dev/null and b/images_4/media/image40.png differ
diff --git a/images_4/media/image41.jpg b/images_4/media/image41.jpg
new file mode 100644
index 00000000..6b9b7890
Binary files /dev/null and b/images_4/media/image41.jpg differ
diff --git a/images_4/media/image42.png b/images_4/media/image42.png
new file mode 100644
index 00000000..3d4bbead
Binary files /dev/null and b/images_4/media/image42.png differ
diff --git a/images_4/media/image43.png b/images_4/media/image43.png
new file mode 100644
index 00000000..04bbb50a
Binary files /dev/null and b/images_4/media/image43.png differ
diff --git a/images_4/media/image44.png b/images_4/media/image44.png
new file mode 100644
index 00000000..2514285d
Binary files /dev/null and b/images_4/media/image44.png differ
diff --git a/images_4/media/image45.png b/images_4/media/image45.png
new file mode 100644
index 00000000..ccc0a398
Binary files /dev/null and b/images_4/media/image45.png differ
diff --git a/images_4/media/image46.png b/images_4/media/image46.png
new file mode 100644
index 00000000..deff43bc
Binary files /dev/null and b/images_4/media/image46.png differ
diff --git a/images_4/media/image47.jpg b/images_4/media/image47.jpg
new file mode 100644
index 00000000..d38a5128
Binary files /dev/null and b/images_4/media/image47.jpg differ
diff --git a/images_4/media/image48.png b/images_4/media/image48.png
new file mode 100644
index 00000000..050992b0
Binary files /dev/null and b/images_4/media/image48.png differ
diff --git a/images_4/media/image5.png b/images_4/media/image5.png
new file mode 100644
index 00000000..585a0644
Binary files /dev/null and b/images_4/media/image5.png differ
diff --git a/images_4/media/image6.jpg b/images_4/media/image6.jpg
new file mode 100644
index 00000000..20205865
Binary files /dev/null and b/images_4/media/image6.jpg differ
diff --git a/images_4/media/image7.jpg b/images_4/media/image7.jpg
new file mode 100644
index 00000000..a7de9ffe
Binary files /dev/null and b/images_4/media/image7.jpg differ
diff --git a/images_4/media/image8.png b/images_4/media/image8.png
new file mode 100644
index 00000000..d5648cfa
Binary files /dev/null and b/images_4/media/image8.png differ
diff --git a/images_4/media/image9.jpg b/images_4/media/image9.jpg
new file mode 100644
index 00000000..60c44fae
Binary files /dev/null and b/images_4/media/image9.jpg differ