• Dr.A.Naresh
• Gaddam Kusum
• Bhimani Dharma Tejaswini
• Garimella Joshitha
• Shaik Reshma

The depth of CNNs allows them to discriminate the various image categories by extracting different levels of features, making it a powerful tool for general object detection and recognition through classification.Training with huge labeled datasets and the usage of powerful computational switches made them extremely accurate within the area of image recognition which skyrocketed improvements in applications such as: medical diagnostics, autonomous vehicles, facial identification systems. In this paper, Small image scale Multiple object detection is a difficult task.Although the computation is slow per multiple scales images and there are not enough memory for end-to-end training in an image architecture. This paper used the technique of Feature Pyramid Network(FPN) to detect images in multi views.This process is independent of the backbone convolutional architectures.It therefore acts as a generic solution for building features pyramids inside deep convolutional networks to be used in tasks like object detection.

Convolutional Layer,Pooling Layer,Activation Function,ReLU (Rectified Linear Unit),Softmax Layer,Filter/Kernels,Stride,Padding,FeatureMaps,TrainingData,Backpropagation,Loss Function.

"CONVOLUTIONAL NEURAL NETWORK (CNN) FOR IMAGE DETECTION AND RECOGNITION ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 10, page no.206-215, October-2024, Available :http://www.jetir.org/papers/JETIRGN06024.pdf

"CONVOLUTIONAL NEURAL NETWORK (CNN) FOR IMAGE DETECTION AND RECOGNITION ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 10, page no. pp206-215, October-2024, Available at : http://www.jetir.org/papers/JETIRGN06024.pdf