Cat dog Classification

Keywords: Cat, dog

Background

Classification of cat and dog is one of the famous datasets that has been used in understanding the differences between the cats and dogs images. There are several different deep learning techniques that can be used in the classification of images dataset. However, CNN models have performed well during the classification of different types of images. There are multiple challenges in the prediction of the image dataset as the size of the image can be varied from each other. Multiple batches must be normalized, and epochs must be increased so that the model can learn a good amount of information from the dataset. They need to be accessed by converting them into the same pixel sizes. However, after a thorough analysis of the two different images, the author has applied the CNN model using multiple max pooling layers. Overall, after a thorough analysis of the different images, the author has achieved an accuracy score of 71%.

Aim & Objectives

Aim
To Classify Cat and Dog Using DL
Objective
Create an ANN model to accurately classify cat and dog images, enhancing visual recognition in diverse applications.
Develop an ANN system that analyzes image features to distinguish between cat and dog subjects.
Evaluate the ANN's classification performance, aiming for reliable differentiation between cat and dog images for various purposes.

Research Methodology

ANN Technique used

Software & Tools

Jupyter, Google Collab

— Preview truncated. The complete document (full chapters, references, diagrams, and appendices) is shared with clients as part of project delivery. —