International Journal of Image, Graphics and Signal Processing (IJIGSP)

IJIGSP Vol. 13, No. 2, Apr. 2021

Cover page and Table of Contents: PDF (size: 657KB)

Table Of Contents

REGULAR PAPERS

Robust Face Detection integrating Novel Skin Color Matching under Variant Illumination Conditions

By Asif Anjum Akash M. A. H. Akhand N. Siddique

DOI: https://doi.org/10.5815/ijigsp.2021.02.01, Pub. Date: 8 Apr. 2021

Integration of skin color property in face detection algorithm is a recent trend to improve accuracy. The existing skin color matching techniques are illumination condition dependent, which directly impacts the face detection algorithm. In this study, a novel illumination condition invariant skin color matching method is proposed which is a composite of two rules to balance the high and low intensity facial images by individual rule. The proposed skin color matching method is incorporated into Haar Feature based Face Detection (HFFD) algorithm for face detection and is verified on a large set of images having variety of skin colors and also varying illumination intensities. Experimental results reveal the effectiveness and robustness of the proposed method outperforming other existing methods.

[...] Read more.
Analog Document Search Using CRNN and Keyphrase Extraction

By Lokeshwar S Vadiraja Rao M. K Sujay Kumar P. S Vishveshwara Guthal Gowda Hemavathi P.

DOI: https://doi.org/10.5815/ijigsp.2021.02.02, Pub. Date: 8 Apr. 2021

There seems to be a peculiar trend in the way information is now used, moving to digital media not just for the newspapers but for books as well. With advances in Optical Character Recognition (OCR), Style Transfer Mapping (STM), and efficient key phrasing, we are now able to digitalize the document to a form that can be read across multiple platforms and searched efficiently. It provides users with the ease of searching for relevant documents without the tedious process of manual searching.
We propose a system that uses the CRNN model to detect English characters in the document with high accuracy. We then pair it with a hybrid keyphrasing technique, which uses Positional Rank as its Graph based rank and re-rank the key phrases using the C-Value method. This process allows us to automatically digitize the printed document and summarise it to provide high-quality keyphrases, which can be used to efficiently search and retrieve relevant printed documents.

[...] Read more.
Medical Image Denoising Techniques against Hazardous Noises: An IQA Metrics Based Comparative Analysis

By Shakil Mahmud Boby Shaela Sharmin

DOI: https://doi.org/10.5815/ijigsp.2021.02.03, Pub. Date: 8 Apr. 2021

Medical imaging has become a vital part of the early detection, diagnosis, and treatment of many diseases. That’s why image denoising is considered as a crucial pre-processing step in medical imaging to restore the original image from its noisy circumstance without losing image features, such as edges, corners, and other sharp structures. Ultrasound (US), Computed Tomography (CT), and Magnetic Resonance (MR) are the most widely used medical imaging techniques that are often corrupted by hazardous noises, namely, speckle, salt and pepper, Poisson, and Gaussian. To remove noises from medical images, researchers have proposed several denoising methods. Each method has its assumptions, merits, and demerits. In this paper, a detailed comparative analysis of different denoising filtering techniques, for example, median, Wiener, mean, hybrid median, Gaussian, bilateral, non-local means, and anisotropic diffusion are performed based on four widely-used image quality assessment (IQA) metrics, such as Root Mean Squared Error (RMSE), Peak Signal to Noise Ratio (PSNR), Mean Absolute Error (MAE), and Structural Similarity Index (SSIM). The results obtained in this present work reveal that Gaussian, median, anisotropic diffusion, and non-local means filtering methods perform extraordinarily to denoise speckle, salt and pepper, Poisson, and Gaussian noises, respectively, from all US, CT, and MR images. 

[...] Read more.
Myanmar Continuous Speech Recognition System Using Convolutional Neural Network

By Yin Win Chit Win Ei Hlaing Myo Myo Khaing

DOI: https://doi.org/10.5815/ijigsp.2021.02.04, Pub. Date: 8 Apr. 2021

Translating the human speech signal into the text words is also known as Automatic Speech Recognition System (ASR) that is still many challenges in the processes of continuous speech recognition. Recognition System for Continuous speech develops with the four processes: segmentation, extraction the feature, classification and then recognition. Nowadays, because of the various changes of weather condition, the weather news becomes very important part for everybody. Mostly, the deaf people can’t hear weather news when the weather news is broadcast by using radio and television channel but the deaf people also need to know about that news report. This system designed to classify and recognize the weather news words as the Myanmar texts on the sounds of Myanmar weather news reporting. In this system, two types of input features are used based on Mel Frequency Cepstral Coefficient (MFCC) feature extraction method such MFCC features and MFCC features images. Then these two types of features are trained to build the acoustic model and are classified these features using the Convolutional Neural Network (CNN) classifiers. As the experimental result, The Word Error Rate (WER) of this entire system is 18.75% on the MFCC features and 11.2% on the MFCC features images.

[...] Read more.
Statistical Texture Features Based Automatic Detection and Classification of Diabetic Retinopathy

By Md. Rahat Khan A. S. M. Shafi

DOI: https://doi.org/10.5815/ijigsp.2021.02.05, Pub. Date: 8 Apr. 2021

Diabetes is a globally prevalent disease that can cause microvascular compilation such as Diabetic Retinopathy (DR) in the human eye organs and it might prompt a significant reason for visual deficiency. The present study aimed to develop an automatic detection and classification system to diagnosing diabetic retinopathy from digital fundus images. An automated diabetic retinopathy detection and classification system from retinal images is proposed in our work to reduce the workload of ophthalmologists. This work comprises three main stages. Our proposed method first extracts the blood vessels from color fundus image. Secondly, the method detects whatever the input image as normal or diabetic retinopathy and then illustrates an automatic diabetic retinopathy classification technique through statistical texture features. It embeds Gray Level Co-occurrence Matrix (GLCM) and Gray Level Run Length Matrix (GLRLM) for second-order and higher-order statistical texture feature as a feature extraction technique into three renowned classifiers namely K-Nearest Neighbor (KNN), Random Forest (RF) and Support Vector Machine (SVM). The evaluation results containing a dataset of 644 retinal images indicate that the proposed method based on random forest classifier is found to be effective with a weighted sensitivity, precision, F1-score and accuracy of 95.53% 96.45%, 95.38% and 95.19% respectively for the detection and classification of diabetic retinopathy. These outcomes propose, that the method could decrease the cost of screening and diagnosis while achieving higher than suggested performance and that the system could be implemented in clinical assessments requiring better evaluating.

[...] Read more.