A whole bunch of different Image processing Projects using OpenCV library covering major aspects of computer vision
Image processing is a method to perform some operations on an image, in order to get an enhanced image or to extract some useful information from it. It is a type of signal processing in which input is an image and output may be image or characteristics/features associated with that image. Its major applications are in detection of motion, objects, activity, color, edges, shapes, etc. For detecting specific objects, the deep learning nets can also be trained upon by using Transfer learning methods.
Detects Color (defined by the HSV ranges) by masking technique.
Detects hand gestures and displays the number corresponding to fingers shown to the screen. Uses the concept of thresholding, contouring, segmentation and convex-hulling.
Detects the motion in the frame. Uses gaussian blurring, absolute difference between present and past frame, contouring etc. methods.
Uses haarcascade files to detect faces, eyes and smile. Uses contour area and bounding boxes methods.
Fundamental and most powerful object detection CNN architecture which works on "You Only Look Once" concept. By the use of trained weights, it is implemented to detect different classes of objects.
Most popular Single Shot Detection (SSD) Neural Network Architecture coded for performing object detection.
- cv2
- Tensorflow
- Keras
- Numpy
- imutils
- sklearn