In many of computer vision applications, the gray levels of pixels belonging to the object are substantia

 In many of computer vision applications, the gray levels of pixels belonging to the object are substantially different from the gray levels of the pixels belonging to the background. Therefore, image thresholding technique is instrumental to the success of many image processing applications. As the input images might be taken at different times of the day, a fixed threshold may not work for different illumination conditions. For this reason, an adaptive thresholding method needs to be incorporated automatically. Otsu has developed a comprehensive statistical technique to find the best threshold for an image. He proposed a criterion for maximizing the between-class variance of pixel intensity to perform image thresholding. This method is accurate for images which contain two distinct classes. On the other hand, to efficiently find the optimal threshold the adaptive progressive thresholding (APT) approach is used as an extension of the Otsu’s technique. 1. Write a program to implement the Otsu's adaptive thresholding technique. Obtain the optimum threshold for segmenting the region of interest (dark object region with respect to a bright background) and create a binary image. Test and evaluate the algorithm on sample images of different types (single object, multiple objects, different lighting and backgrounds etc., see Project-Data) 2. Write a program to implement the adaptive progressive thresholding (APT) technique. Obtain the optimum final threshold for segmenting the region of interest (dark object region with respect to a bright background) and create a binary image. Test and evaluate the algorithm on sample images of different types (single object, multiple objects, different lighting and backgrounds etc., see Project-Data) Notes: • The project should be implemented in Python. • Only one single file should be submitted through Blackboard for evaluation, which includes: ✓ The project report that includes the methodology, equations used, implementation results and discussion, conclusion, appropriate technical references, etc. ✓ The program codes along with the dataset used for testing and validation. • Late submissions will not be accepted. • Email submissions will not be accepted.