Dog Breed Classification using Inception-ResNet-V2
Dog Breed Classification using Deep learning
IEEE Base Paper Title:
Dog Breed Classification using Inception-ResNet-V2
(or)
Our Proposed Project Title:
DeepDoggo: Accurate Dog Breed Classification using Xception Architecture
IEEE BASE PAPER ABSTRACT:
Dogs are one of the most faithful and loyal animals in the world. They are also the favourite pets for most of the pet lovers. Many feel relieved from stress and tension when they spent time with their pet dogs. So these special creatures are spread into various breeds across the world. It is very much essential to distinguish the breeds at many occasions. With the advent of development of artificial intelligence the methods to classify such large scale of breeds had become easier. This paper proposes a transfer learning based pretrained deep CNN architecture for classification of 120 breeds. The proposed model was trained on Stanford dogs dataset and the model achieved a training accuracy of 95.03% and a validation accuracy of 92.92% after training. The model performance and robustness had been inferred after testing with test images from internet. The network predicted correct breeds with a test accuracy of 88.92%.This paper provides an optimal solution for fine grained dog breed classification.
PROJECT OUTPUT VIDEO:
ALGORITHM / MODEL USED:
Xception Architecture.
OUR PROPOSED ABSTRACT:
The dog breed classification is not only fascinating from a scientific perspective but also holds practical significance in various aspects of animal care, veterinary medicine, and human-animal interactions. By understanding the unique characteristics and needs of different breeds, we can improve the well-being and welfare of dogs and enhance our relationship with our canine companions.
In this project titled “Dog Breed Classification using Deep Learning,” we present a novel approach to accurately classify dog breeds in images utilizing the powerful capabilities of the Xception Architecture. Developed in Python, our deep learning model demonstrates outstanding performance with a remarkable training accuracy of 91.34% and a validation accuracy of 89.45%.
The heart of our methodology lies in a carefully curated dataset containing 7,515 dog images, encompassing an impressive 133 diverse dog breed classifications. Leveraging the vastness of this dataset, our model exhibits exceptional generalization and robustness, enabling it to discern intricate differences between various dog breeds. Through the implementation of the Xception Architecture, we achieve a higher level of feature extraction and representation, enabling our model to discern intricate patterns and features within the images, leading to its remarkable classification prowess.
The utilization of this cutting-edge architecture ensures that our model efficiently learns from the dataset and captures the subtle nuances that differentiate one dog breed from another. The attained results exemplify the effectiveness of our approach in tackling the challenging task of dog breed classification, outperforming conventional methods. The high training and validation accuracies demonstrate the model’s ability to learn and generalize effectively, even when faced with an extensive range of dog breeds.
This Dog Breed Classification system presents a significant advancement in the domain of image classification using deep learning, showcasing the potential of the Xception Architecture for solving intricate real-world problems. The obtained results underscore the importance of utilizing sophisticated deep learning techniques and carefully curated datasets to achieve state-of-the-art performance in breed recognition tasks, with applications in animal welfare, veterinary science, and beyond.
SYSTEM REQUIREMENTS:
HARDWARE REQUIREMENTS:
- System : Pentium i3 Processor.
- Hard Disk : 500 GB.
- Monitor : 15’’ LED
- Input Devices : Keyboard, Mouse
- Ram : 6 GB
SOFTWARE REQUIREMENTS:
- Operating system : Windows 10 / 11.
- Coding Language : Python 3.10.9
- Web Framework : Flask.
- Frontend : HTML, CSS, JavaScript.
REFERENCE:
Manivannan; N. Venkateswaran, “Dog Breed Classification using Inception-ResNet-V2”, 2023 International Conference for Advancement in Technology (ICONAT), IEEE Conference, 2023.