ABSTRACT
One of the most significant areas of image processing and computer vision is object detection. In modern days, Humans have a tendency to grasp things fast when we teach them in a practical way. The proposed system is designed to learn the correspondence between preached words and conceptual visual attributes from a spoken image description dataset. For this purpose, vision technology and neural network algorithm are used to do image enhancement and manipulation techniques using LABVIEW platform. First, train the PC with OCR (Optical Character Recognition) technique and continue this process for 2-3 times so that it becomes accurate. Then with the help of the KNN algorithm, an input image is compared with the predefined dataset. The acquisition and processing of images are done in the graphical programming environment of LabVIEW. This gives all the benefits of this software to the application: modularity, effortless realization, desirable user interface, springiness, and the ability to develop very simple new features. The learner can use the proposed scheme to learn things in a smarter way.
