Abstract
This project focuses on detection of sign for hand gesture techniques and introduces merits and drawbacks in various circumstances. The hand segmentation theory and hand detection system is used for constructing hand gesture recognition by using Python with OpenCV. The hand gesture is as a natural interface which motivates research in gesture taxonomies, representations, and recognition methods/algorithms and software platforms/ frameworks, all of which are covered with detail in this project. The ever increasing public acceptance and fund for multinational projects emphasizes need for sign language. The desire for computer-based solution is important in recent age of technology for deaf people. Still, researchers are studying the problem for quite sometimes and results are showing promises. This project represents the comprehensive review of vision oriented sign recognition methodologies, emphasizing importance of taking things into consideration moreover with algorithm's recognition accuracy during predicting the success in real world scenario. This project matches given image with dataset images with numerous categories of sign (gestures). Here the convolutional neural network (CNN) has been implemented to increase the accuracy level. This project applies gray scale conversion, then binary image conversion and finally histogram construction and matching of given test image with data set images. The coding language used is Python 3.8.