Abstract: Classifying sea animals is an important problem in marine biology and ecology as it enables the accurate identification and monitoring of species populations, which is crucial for understanding and protecting marine ecosystems. This paper addresses the problem of classifying 19 different sea animals using convolutional neural networks (CNNs). The proposed solution is to use a pretrained MobileNetV2 model, which is a lightweight and efficient CNN architecture, and fine-tune it on a dataset of sea animals. The results of the (...) study show that the fine-tuned MobileNetV2 model is able to achieve an accuracy of 85% on the classification task, which is competitive with the state-of-the-art methods. Additionally, the study also found that data augmentation and regularization techniques such as dropout were important for preventing overfitting and improving the performance of the model. This study demonstrates the potential of using pretrained models and efficient CNN architectures for classifying sea animals, and it provides insights into the challenges and best practices for solving this important problem in marine biology and ecology. (shrink)

The project is aimed at an arduous task of precise identification of medicinal plant species with the problem being pertinent in those industries that include botany, Ayurveda, pharmacology, and biomedical research. Most of the traditional identification methods are quite serious challenges for users, researchers, and students because they are usually time-consuming, knowledge-intensive, and prone to human errors. Our proposal develops an advanced web-based application for this process by utilizing state-of-the-art methods in image processing and machine learning. We will create a (...) platform where users can upload or take pictures of plant specimens and obtain accurate identifications and comprehensive medical information by using machine learning algorithms with plant species image datasets. This application is done in a way that the interface would be user-friendly and favor research, identification, and learning, especially for Ayurvedic practitioners, biomedical specialists, botanists, and students. Therefore, our project is aimed at developing an exhaustive and reliable solution for medicinal plant identification and study by overcoming the deficiencies of existing systems, such as a small dataset, poor variable quality, and lack of complete medicinal information. (shrink)

For Insect Classification there are many methods proposed. To find the more suitable classifier we have implemented two different methods of classification, Custom CNN and Transfer Learning. We observed the accuracy and loss parameters during training phase and validation phase on both Custom CNN and Transfer learning methods. In Transfer Learning we have created the base model from the pre-trained model MobileNetV2. This model is further trained on Imagenet Dataset which consists of 1.2M labeled images .We compared all attributes (...) of both models on this dataset. Recorded Accuracy and Loss for training and Validation. From the results we found that Custom CNN model works better than Transfer Learning for this dataset. This model can also be used for education and farming purpose. (shrink)

The corona virus COVID-19 pandemic is causing a global health crisis so the effective protection methods is wearing a face mask in public areas according to the World Health Organization (WHO). The COVID-19 pandemic forced governments across the world to impose lockdowns to prevent virus transmissions. Reports indicate that wearing facemasks while at work clearly reduces the risk of transmission. An efficient and economic approach of using AI to create a safe environment in a manufacturing setup. A hybrid model using (...) deep and classical machine learning for face mask detection will be presented. A face mask detection dataset consists of with mask and without mask images, we are going to use OpenCV to do real-time face detection from a live stream via our webcam. We will use the dataset to build a COVID-19 face mask detector with computer vision using Python, OpenCV, and Tensor Flow and Keras. Our goal is to identify whether the person on image/video stream is wearing a face mask or not with the help of computer vision and deep learning. (shrink)