Design and Development of Fine-Grained Image classification

Fine-Grained Image classification is an area of machine learning in which we can perform classification between the same categories such as dog breeds, where we can determine the breed of dog. At present fine-grained image classification has developed variety of methods including multi-network learning, target part detection and visual attention. Each method is to obtain a distinguishing area in the image, which help the network to learn more effective features to complete the classification and recognition of fine-grained image. In this paper, we introduce an image dataset for fine-grained classification of dog breed: Kaggle’s Dog Database. The database consists of 120 dog breeds which contains at least 60 images of each breed. It helps for the accurate prediction of images with its accuracy percentage. We tested our model and result of our model show that our proposed model can achieve the desire result.