Adaptive Rate Polar Code for DCT-Based Digital Image Transmission

Abstract

Polar code is a recent forward error correction technique that is characterized by its low encoding/decoding complexity and good error performance. In this paper, a complete image transmission system (transmitter and receiver) is proposed to improve the image quality over different types of channels such as Gaussian, Rayleigh and Rician channels. The proposed system is based on encoding the most significant quantized Discrete Cosine Transform (DCT) coefficients of the digital image using adaptive rate polar coding, by changing the number of frozen bits depending on the number of significant DCT coefficients that depend on the channel quality. Simulation results reveal that the proposed system achieves better performance compared to the coded digital transmission schemes in terms of the Structural SIMilarity (SSIM) index and the Peak Signal to Noise Ratio (PSNR) for different sizes of images. Moreover, it is not subject to ''cliff effect'' and exhibits improvement in image quality according to the channel quality.INDEX TERMS Adaptive rate, cliff effect, DCT, frozen bits, image transmission, polar code.

New Face Recognition System Based on DCT Pyramid and Backpropagation Neural Network

“…Accurate identification of individuals plays a crucial role in improving security measures, optimising access control systems, and mitigating fraudulent activities. Among the various biometric modalities, facial recognition has emerged as an especially notable and promising approach due to its non-intrusive nature, real-time functionality, and adaptability to diverse environments [1]- [3]. Traditional facial recognition techniques involve two main steps, namely feature extraction and classification [1]- [3].…”

“…Among the various biometric modalities, facial recognition has emerged as an especially notable and promising approach due to its non-intrusive nature, real-time functionality, and adaptability to diverse environments [1]- [3]. Traditional facial recognition techniques involve two main steps, namely feature extraction and classification [1]- [3]. The former aims to capture the distinguishing characteristics of a face from an image, while the latter uses these extracted features to identify the individual [2], [3].…”

“…Traditional facial recognition techniques involve two main steps, namely feature extraction and classification [1]- [3]. The former aims to capture the distinguishing characteristics of a face from an image, while the latter uses these extracted features to identify the individual [2], [3]. Various feature extraction methods have been employed in the literature, such as local binary patterns (LBP) [4], [5], eigenfaces [6], [7], Gabor filters [8], and histogram of oriented gradients (HOG) [9].…”

“…On the other hand, decision trees use a hierarchical structure to classify images based on different facial features [25]. However, traditional techniques are less robust when faced with occlusions such as sunglasses, hats, or facial hair, as these may interfere with the feature extraction process and affect classification accuracy [2], [3], [26]. Moreover, traditional methods might struggle to handle noisy or low-quality images, leading to reduced recognition performance in such cases [2], [3].…”

“…However, traditional techniques are less robust when faced with occlusions such as sunglasses, hats, or facial hair, as these may interfere with the feature extraction process and affect classification accuracy [2], [3], [26]. Moreover, traditional methods might struggle to handle noisy or low-quality images, leading to reduced recognition performance in such cases [2], [3]. Deep learning has revolutionised the field of facial recognition by offering significant improvements in accuracy [2], [3].…”