INTEGRATING MACHINE LEARNING TECHNIQUES FOR ENHANCED OBJECT RECOGNITION IN OBJECT – ORIENTED PROGRAMMING ENVIRONMENTS

As object-oriented programming (OOP) continues to be a relevant programming concept in software development, the complexity of identifying and classifying objects within large-scale systems poses significant challenges. This study explores the integration of machine learning (ML) techniques within object-oriented programming (OOP) environments to enhance object recognition capabilities. The case study methodology was adopted to model the system as a classification and detection problem. This approach utilized feature extraction and clustering techniques to recognize objects and their interactions, enabling automated code analysis, bug detection and prediction of object behavior. The model enables OOP environments to learn from data, recognize patterns and make predictions, thereby enhancing overall system performance and reliability. The system used a hybrid algorithm that combined computer vision and machine learning techniques to detect and classify objects and human attributes from images. Furthermore, the system was implemented using full-stack approach combining back-end processing and front end interaction to train the ML model and load functions. Experimental results demonstrated significant improvements in object recognition accuracy, reducing development time and increasing software reliability. This article contributes to the advancement of intelligent software engineering tools, paving the way for more efficient and adaptive OOP systems. This study used the interpretive paradigm, through deductive analysis to draw the conclusion that the level of integration of ML in object recognition applications is relatively poor and therefore recommends that software developers should adopt a ML approach for object recognition using OOP environments such as TensorFlow, PyTorch or OpenCV. Word count: 242