Search

Underwater images hold immense value for various fields, including marine biology research, underwater infrastructure inspection, and exploration activities. However, capturing high-quality images underwater proves challenging due to light absorption and scattering leading to color distortion, blue green hues. Additionally, these phenomena decrease contrast and visibility, hindering the ability to extract valuable information. Existing image enhancement methods often struggle to achieve accurate color correction while preserving crucial image details. This article proposes a novel deep learning-based approach for underwater image enhancement that leverages the power of autoencoders. Specifically, a convolutional autoencoder is trained to learn a mapping from the distorted colors present in underwater images to their true, color-corrected counterparts. The proposed model is trained and tested using the Enhancing Underwater Visual Perception (EUVP) and Underwater Image Enhancement Benchmark (UIEB) datasets. The performance of the model is evaluated and compared with various traditional and deep learning based image enhancement techniques using the quality measures structural similarity index (SSIM), peak signal-to-noise ratio (PSNR) and mean squared error (MSE). This research aims to address the critical limitations of current techniques by offering a superior method for underwater image enhancement by improving color fidelity and better information extraction capabilities for various applications. Our proposed color correction model based on encoder decoder network achieves higher SSIM and PSNR values.

Facial Emotion Recognition (FER) maps diverse facial emotions to a wide variety of emotional states. Different facial emotions and expressions play a significant role in the communication of emotions via non-verbal channels, making them an extremely efficient technique for expressing humans’ internal thoughts to society. Facial emotions have been applied in a wide range of applications, such as healthcare, cyber-security, human-machine interfaces, and more. Over the past decades, FER has become a challenging research problem addressed by several researchers using different Machine Learning (ML) and Deep Learning (DL) techniques. However, in psychological patients, their emotions are often associated with various mental health issues. To address this, the paper presents a review of several DL techniques and infers that ResNet-50 is the best classifier for predicting mental health via facial emotions/expressions, achieving an efficient accuracy of 95.39% with minimal time complexity. [ABSTRACT FROM AUTHOR]

ABSTRACT A conventional content‐based image retrieval system (CBIR) extracts image features from every pixel of the images, and its depiction of the feature is entirely different from human perception. Additionally, it takes a significant amount of time for retrieval. An optimal combination of appropriate image features is necessary to bridge the semantic gap between user queries and retrieval responses. Furthermore, users should require minimal interactions with the CBIR system to obtain accurate responses. Therefore, the proposed work focuses on extracting highly relevant feature information from a set of images in various natural image databases. Subsequently, a feature‐based learning/classification model is introduced before similarity measure calculations, aiming to minimise retrieval time and the number of comparisons. The proposed work analyses the learning models based on the retrieval system's performance separately for the following features: (i) dominant colour, (ii) multi‐resolution radial difference texture patterns, and a combination of both. The developed work is assessed with other techniques, and the results are reported. The results demonstrate that the implemented ensemble learning model‐based CBIR outperforms the recent CBIR techniques. [ABSTRACT FROM AUTHOR]

The images involved in the content-based image retrieval (CBIR) applications are collectively represented by features such as color, texture and shape. The precision of the CBIR application relies on the key features used in image representation and its similarity measure. In CBIR, dominant color feature extraction is affected by the predefined intervals used in color quantization. The proposed work mainly concentrates on extracting the dominant color information of the image using the clustering process. The clustering process is initiated by the proposed seed point's selection approach. This approach derives the number of seed points using the first order statistical measure and maximum range of the distributed pixel values. Moreover, this work gives equal priority to dominant color and its occurrence information in calculating the similarity between query and database images. Finally, the standard databases such as SIMPLIcity, Corel-10k, OT-scene, Oxford flower and GHIM are taken to investigate the performance of the proposed dominant color based image retrieval application. [ABSTRACT FROM AUTHOR]