Object segmentation and recognition is an imperative area of computer vision and machine learning that identifiesand separates individual objects within an image or video and determines classes or categories based on theirfeatures. The proposed system presents a distinctive approach to object segmentation and recognition usingArtificial Neural Networks (ANNs). The system takes RGB images as input and uses a k-means clustering-basedsegmentation technique to fragment the intended parts of the images into different regions and label them based ontheir characteristics. Then, two distinct kinds of features are obtained from the segmented images to help identifythe objects of interest. An Artificial Neural Network (ANN) is then used to recognize the objects based on theirfeatures. Experiments were carried out with three standard datasets, MSRC, MS COCO, and Caltech 101 whichare extensively used in object recognition research, to measure the productivity of the suggested approach. Thefindings from the experiment support the suggested system’s validity, as it achieved class recognition accuracies of89%, 83%, and 90.30% on the MSRC, MS COCO, and Caltech 101 datasets, respectively.