Image Quality Assessment Techniques Research Articles

Image-Based Detection and Classification of Malaria Parasites and Leukocytes with Quality Assessment of Romanowsky-Stained Blood Smears.

Malaria remains a global health concern, with 249 million cases and 608,000 deaths being reported by the WHO in 2022. Traditional diagnostic methods often struggle with inconsistent stain quality, lighting variations, and limited resources in endemic regions, making manual detection time-intensive and error-prone. This study introduces an automated system for analyzing Romanowsky-stained thick blood smears, focusing on image quality evaluation, leukocyte detection, and malaria parasite classification. Using a dataset of 1000 clinically diagnosed images, we applied feature extraction techniques, including histogram bins and texture analysis with the gray level co-occurrence matrix (GLCM), alongside support vector machines (SVMs), for image quality assessment. Leukocyte detection employed optimal thresholding segmentation utility (OTSU) thresholding, binary masking, and erosion, followed by the connected components algorithm. Parasite detection used high-intensity region selection and adaptive bounding boxes, followed by a custom convolutional neural network (CNN) for candidate identification. A second CNN classified parasites into trophozoites, schizonts, and gametocytes. The system achieved an F1-score of 95% for image quality evaluation, 88.92% for leukocyte detection, and 82.10% for parasite detection. The F1-score-a metric balancing precision (correctly identified positives) and recall (correctly detected instances out of actual positives)-is especially valuable for assessing models on imbalanced datasets. In parasite stage classification, CNN achieved F1-scores of 85% for trophozoites, 88% for schizonts, and 83% for gametocytes. This study introduces a robust and scalable automated system that addresses critical challenges in malaria diagnosis by integrating advanced image quality assessment and deep learning techniques for parasite detection and classification. This system's adaptability to low-resource settings underscores its potential to improve malaria diagnostics globally.

An improved modal tracking algorithm for dispersion analysis of arbitrary prestressed plates

Determining the dispersion characteristics of prestressed plates is essential for guided wave-based structural health monitoring, which can provide theoretical guidance for optimizing excitation mode and frequency. However, the multi-mode nature of guided waves brings huge challenges for modal tracking. Conventional methods require sufficiently small frequency steps and may encounter tracking errors during mode crossing and overlap. To address these issues, this paper established a multi-step superposition model to obtain the dispersion relation of arbitrary prestressed plates and proposed a novel modal tracking method based on structural similarity (SSIM) image registration for identifying all guided wave modes. Drawing inspiration from the image quality assessment technique, a novel index was introduced to evaluate the consistency between modal eigenvectors quantitatively. Furthermore, an improved algorithm using eigenvector operations was developed to further enhance the efficiency and applicability of the modal tracking process. Subsequently, application examples were conducted to thoroughly evaluate the performance of the proposed methods through comparison with conventional modal tracking methods. The results indicated that the proposed methods have accurate and reliable tracking performance even with larger wavenumber steps, which is unattainable with conventional methods. Notably, the computational efficiency of the improved algorithm is nearly 13 times faster than the SSIM-based image registration method. Finally, an investigation into the dispersion characteristics of aluminum plates under tensile, bending, and shear stress demonstrated the versatility of the improved modal tracking algorithm. This study provides valuable insights into the dispersion behavior of guided waves in prestressed plates.

Rice Grains Detection, Classification, and Quality Prediction Using Deep Learning

Abstract: Rice, as the most consumed food worldwide, faces a continual demand, necessitating rigorous quality inspection for both local consumption and international trade. Manual quality assessment methods are fraught with issues such as time consumption, high costs, and error susceptibility. This research paper introduces an innovative solution employing Deep Convolutional Neural Networks (CNNs) to automate rice grain detection, classification, and quality prediction from scanned images. The methodology integrates comprehensive image pre-processing and quality assessment techniques, encompassing image acquisition, pre-processing, CNN architecture construction, model training, and evaluation. Notably, it includes noise removal and segmentation to optimize input images. The grain samples undergo image processing using MATLAB, where an algorithm is applied to analyze their features. Classification is then performed based on the color, shape, and size characteristics of the grains. Various image features are extracted such as centroids, mean intensity, chalkiness, and perimeter further aid in quality assessment. Performance evaluation of the trained model is conducted through confusion matrix analysis and computation of classification metrics like accuracy, specificity, sensitivity, precision, recall, and F1-score. This methodology offers a robust framework for automated rice grain classification and quality prediction, thereby significantly enhancing efficiency and reliability in the global rice industry

A Literature Survey on Completely Blind Image Quality Evaluator Feature-Enriched

Existing blind image quality assessment (BIQA) technique in which are principally opinion-aware. They learn deterioration models from training photos with associated human subjective scores to predict the sensory activity quality of take a look at pictures. Such opinion-aware methods, however, need a bulky amount of training example with associated human prejudiced achieve moreover of a variety of deformation category. The BIQA representation find out through opinion-aware strategies typically have weak generalization capability, herewith limiting their usability in observe. By comparison, opinion-unaware strategies don't require human prejudiced achieve for training, and then have superior possible designed for good quality simplification ability. Unluckily, to the present point no opinion-unaware BIQA technique has shown systematically better quality prediction accuracy than the opinion-aware strategies. Here, we tend to aim to develop an opinionunaware BIQA technique that may compete with, and maybe exceed, the present opinion-aware methods. By integration the options of ordinary picture information consequent as of multiple cues, we have an affinity to discover a multivariate Gaussian structure of representation patches from a set of perfect natural pictures. using the learned multivariate Gaussian form, a Bhattacharyya-like distance is employed to measure the standard of every image patch, and then a generally value score is find by average pooling. The projected BIQA technique doesn't want any distorted sample images or subjective class achieve for training, yet extensive experiment show its better quality-prediction presentation to the situation of the art opinion-aware BIQA strategies.

A Literature Survey on Completely Blind Image Quality Evaluator Feature-Enriched

Existing blind image quality assessment (BIQA) technique in which are principally opinion-aware. They learn deterioration models from training photos with associated human subjective scores to predict the sensory activity quality of take a look at pictures. Such opinion-aware methods, however, need a bulky amount of training example with associated human prejudiced achieve moreover of a variety of deformation category. The BIQA representation find out through opinion-aware strategies typically have weak generalization capability, herewith limiting their usability in observe. By comparison, opinion-unaware strategies don't require human prejudiced achieve for training, and then have superior possible designed for good quality simplification ability. Unluckily, to the present point no opinion-unaware BIQA technique has shown systematically better quality prediction accuracy than the opinion-aware strategies. Here, we tend to aim to develop an opinionunaware BIQA technique that may compete with, and maybe exceed, the present opinion-aware methods. By integration the options of ordinary picture information consequent as of multiple cues, we have an affinity to discover a multivariate Gaussian structure of representation patches from a set of perfect natural pictures. using the learned multivariate Gaussian form, a Bhattacharyya-like distance is employed to measure the standard of every image patch, and then a generally value score is find by average pooling. The projected BIQA technique doesn't want any distorted sample images or subjective class achieve for training, yet extensive experiment show its better quality-prediction presentation to the situation of the art opinion-aware BIQA strategies.

On evaluation of image quality in nonparaxial single-pixel imaging

High numerical apertures lead to an appearance of distortions in a single-shot image, which make obtaining images troublesome if not impossible. These obstacles can be overcome in single-pixel imaging, where different strategies lead to inspection of objects with a good resolution, contrast and brightness. Recent advances in flat photonic elements have enabled the creation of compact nonparaxial imaging systems, which are especially promising in the THz range of wavelengths, bringing advances to such fields as communication, material inspection and spectroscopy. In this work, we dive into the problematics of single-pixel imaging: we introduce an object sample, which we use to investigate the resolution, contrast and brightness of the classical two-lens imaging setup. We evaluate the nonparaxial imaging of the sample and report that the conditions for the best contrast and the best brightness are decoupled in nonparaxial single pixel imaging. To overcome this hurdle, we use two integral image quality assessment techniques from computational imaging theory and estimate the quality of the image in a virtual numerical THz imaging scenario. The localized mean square error metric did not cause additional constraints to the quality of the image, whereas the global mean square error has restricted the range of possible imaging setups. Thus, the computational integral image quality assessment techniques back up the main claim of this study that in the single-pixel imaging the resolution is decoupled from the image brightness.

Quality and Feature Analysis of Parent and Child Fingerprints in West Bengal, India

Abstract: Fingerprint image of father, mother and child in ink paper method are collected from the region of West Bengal, India. One Hundred family without having kinship relation are involved in the data collection process. The paper is scanned with a HP scanner with 1200 ppi resolution and pre-processed with different technique to form a dataset of 1500 fingerprint images. Different non reference and reference image quality assessment technique are applied to test the quality of the image dataset. Minutiae based feature are extracted from the images to find a correlation between child and parent’s fingerprints. This family fingerprint dataset can be used by the researchers to find an alternative of DNA matching for parental verification or other research works.

BPG-based compression analysis of Poisson-noisy medical images

The subject matter is lossy compression using the BPG encoder for medical images with varying levels of visual complexity, which are corrupted by Poisson noise. The goal of this study is to determine the optimal parameters for image compression and select the most suitable metric for identifying the optimal operational point. The tasks addressed include: selecting test images sized 512x512 in grayscale with varying degrees of visual complexity, encompassing visually intricate images rich in edges and textures, moderately complex images with edges and textures adjacent to homogeneous regions, and visually simple images primarily composed of homogeneous regions; establishing image quality evaluation metrics and assessing their performance across different encoder compression parameters; choosing one or multiple metrics that distinctly identify the position of the optimal operational point; and providing recommendations based on the attained results regarding the compression of medical images corrupted by Poisson noise using a BPG encoder, with the aim of maximizing the restored image’s quality resemblance to the original. The employed methods encompass image quality assessment techniques employing MSE, PSNR, MSSIM, and PSNR-HVS-M metrics, as well as software modeling in Python without using the built-in Poisson noise generator. The ensuing results indicate that optimal operational points (OOP) can be discerned for all these metrics when the compressed image quality surpasses that of the corresponding original image, accompanied by a sufficiently high compression ratio. Moreover, striking a suitable balance between the compression ratio and image quality leads to partial noise reduction without introducing notable distortions in the compressed image. This study underscores the significance of employing appropriate metrics for evaluating the quality of compressed medical images and provides insights into determining the compression parameter Q to attain the BPG encoder’s optimal operational point for specific images. Conclusions. The scientific novelty of the findings encompasses the following: 1) the capability of all metrics to determine the OOP for images of moderate visual complexity or those dominated by homogeneous areas; MSE and PSNR metrics demonstrating superior results for images rich in textures and edges; 2) the research highlights the dependency of Q in the OOP on the average image intensity, which can be reasonably established for a given image earmarked for compression based on our outcomes. The compression ratios for images compressed at the OOP are sufficiently high, further substantiating the rationale for compressing images in close proximity to the OOP.

Image Focus Measure Based on Polynomial Coefficients and Reduced Gerschgorin Circle Approach

In this paper, a simple and efficient no-reference image quality assessment technique based on polynomial coefficient and reduced Gerschgorin circle is presented. The dominant features and dynamics of the test images are captured using the polynomial coefficient. Moreover, the image focus measure is modeled using the concept of reduced Gerschgorin's higher circle bound. The presented image focus measure is tested on different synthetic images datasets such as LIVE, TID2008, CSIQ, Cornel and IVC. Further, the proposed approach is also examined on real-time images captured by the camera in different conditions. It is observed that the proposed approach demonstrates important properties of focus measures such as unimodality and contrast invariance. Moreover, the presented technique is robust under the different varying noisy conditions.

NITS-IQA Database: A New Image Quality Assessment Database.

This paper describes a newly-created image database termed as the NITS-IQA database for image quality assessment (IQA). In spite of recently developed IQA databases, which contain a collection of a huge number of images and type of distortions, there is still a lack of new distortion and use of real natural images taken by the camera. The NITS-IQA database contains total 414 images, including 405 distorted images (nine types of distortion with five levels in each of the distortion type) and nine original images. In this paper, a detailed step by step description of the database development along with the procedure of the subjective test experiment is explained. The subjective test experiment is carried out in order to obtain the individual opinion score of the quality of the images presented before them. The mean opinion score (MOS) is obtained from the individual opinion score. In this paper, the Pearson, Spearman and Kendall rank correlation between a state-of-the-art IQA technique and the MOS are analyzed and presented.

Investigating pretrained self-supervised vision transformers for reference-based quality assessment

Reference-based image quality assessment techniques use information from an undistorted reference image of the same scene to estimate the quality of a distorted target image. The main challenge in designing algorithms for quality assessment is to incorporate the behavior of the human visual system into the algorithms. The advent of deep learning (DL) techniques has garnered sufficient interest among researchers in the field of image quality assessment. The common limitation of applying deep learning for image quality assessment is its dependence on a large amount of subjective training data. Recent advances in the field of patch-based self-supervised vision transformers have achieved remarkable results for tasks like object segmentation, copy detection, etc. and other downstream computer vision tasks. In this paper, we study how the distance between the pretrained self-supervised vision transformer features applied on pristine and distorted images is related to the human visual system. Experiments carried out on three publicly available image quality databases (namely KADID-10K, TID2013, and MDID2016) have yielded promising results that can be further exploited to design perceptual reference-based image quality assessment methods.

Image quality assessment: Intelligent feature selection using soft computing techniques

Image Quality Assessment (IQA), the quantification of a human’s perception of qualityof an image, is a rudimentary problem visual communication system, and beholds unparalleled significance in diverse practical applications like image compression, restoration, and, rendering. The limitations of conventional IQA parameters have motivated the researchers to go for IQA techniques based on the Soft Computing meta-heuristic algorithms that are able to extract features intelligently. In current paper, Whale Optimization Algorithm (WOA) has been applied, which is a meta-heuristic algorithm grounded on swarm behaviour. This technique mimics the demeanor of humpback whales for finding an optimal solution. For the purpose of extensive analysis and testing in Matlab, Colourlab Image Database: Image Quality (CID:IQ) benchmark dataset is applied. Tabular, as well as graphical outcomes, are defended for validating the effectiveness of WOA as compared to traditional methods. WOA understandably surmounts Artificial Neural Networks (ANN) based optimization with regards to Peak Signal to Noise Ratio (PSNR), Mean Square Error (MSE), and other popular IQA parameters. This amelioration is capable of motivating the researchers in the time to come for opting the soft computing mechanisms in several image processing arenas that includes but is not limited to the agricultural sciences, medicine, remote sensing, etc., for assessing the images in pre-processing stages to achieve ameliorated results.

SDNET2021: Annotated NDE Dataset for Subsurface Structural Defects Detection in Concrete Bridge Decks

Annotated datasets play a significant role in developing advanced Artificial Intelligence (AI) models that can detect bridge structure defects autonomously. Most defect datasets contain visual images of surface defects; however, subsurface defect data such as delamination which are critical for effective bridge deck evaluations are typically rare or limited to laboratory specimens. Three Non-Destructive Evaluation (NDE) methods (Infrared Thermography (IRT), Impact Echo (IE), and Ground Penetrating Radar (GPR)) were used for concrete delamination detection and reinforcement corrosion detection. The authors have developed a unique NDE dataset, Structural Defect Network 2021 (SDNET2021), which consists of IRT, IE, and GPR data collected from five in-service reinforced concrete bridge decks. A delamination survey map locating the areas, extent and classes of delamination served as the ground truth for annotating IRT, IE and GPR field tests’ data in this study. The IRT were processed to create an ortho-mosaic maps for each deck and were aligned with the ground truth maps using image registration, affine transformation, image binarization, morphological operations, connected components and region props techniques to execute a semi-automatic pixel–wise annotation. Conventional methods such as Fast Fourier transform (FFT)/peak frequency and B-Scan were used for preliminary analysis for the IE and GPR signal data respectively. The quality of NDE data was verified using conventional Image Quality Assessment (IQA) techniques. SDNET2021 dataset consists of 557 delaminated and 1379 sound IE signals, 214,943 delaminated and 448,159 sound GPR signals, and about 1,718,083 delaminated and 2,862,597 sound IRT pixels. SDNET2021 addresses one of the major gaps in benchmarking, developing, training, and testing advanced deep learning models for concrete bridge evaluation by providing a publicly available annotated and validated NDE dataset.

A Brief Review of Image Quality Assessment Techniques for Laparoscopic Image Restoration

Laparoscopic images usually suffer image degradation due to smoking, insufficient illumination, specularity, and limited fields of view. Computer-assisted restoration algorithms have been developed to tackle this problem, whose performance needs to be assessed through a mechanism of image quality evaluation. In this study, we will briefly exam several image quality assessment technologies that have been utilized in the process of laparoscopic image restoration.

Image Quality Assessment of No Reference JPEG Compressed Images Using Various Spatial Domain Features

In today's world of technological advancement higher data rate and data transmission with minimal memoryrequirement is gaining importance. At the same time it also important to preserve quality of data to be transferredfrom various types of distortions and to assess the quality at the receiving end. Hence perceptual image qualityassessment is becoming more popular. This paper introduces a new approach in domain of no reference imagequality assessment of jpeg compressed images using spatial features .Considering the fact that pixel distortion,blurring and edge information are important aspects as far as distortions are concern. A novel approach is presentedin this paper to address the distortion categories. The results are obtained in conjunction with the subjectiveimage quality assessment of train and test image categories. Also results are compared with full reference imagequality assessment technique and parameters of full reference quality assessment. To achieve better accuracyalgorithm is tested on LIVE Texas' image database and our own developed database. Results are found to be wellcorrelating to the various parameters considered for the comparison purpose.

Image Quality Assessment: Edge Based Entropy features estimation using Soft Computing Techniques

With the always expanding interest for image handling based applications, the requirement for Image Quality Assessment (IQA) techniques for proficient and dependable assessment of picture quality in concurrence with human quality decisions has similarly taken off at each phase of image processing. The limits of customary IQA strategies as far as having the option to work just under a pre-characterized set of filtering algorithms confines the effectiveness of methods in explicit degradations has roused the investigation of IQA dependent on Soft Computing metaheuristic techniques, which are equipped for choosing the features shrewdly. A swarm based meta heuristic technique known as Grey Wolf Optimization (GWO) has been utilized, which impersonates the conduct of wolf packs to encompass and chase their prey. This paper presents a basic and direct strategy for artificially assessing computerized images by a solitary parameter, entropy. The benchmark dataset Colourlab Image Database: Image Quality (CID:IQ) is employed for the extensive Matlab investigations. Outcomes are addressed graphically to approve the viability of GWO algorithm over others. GWO evidently surmounts Artificial Neural Networks (ANN) based optimization algorithm in terms of entropy. These meliorations are likely to propel the future researchers to prefer the soft computing techniques for use in different image handling areas including horticultural sciences, medication, cryptography, and so on, for evaluating their images in pre-processing phases for improved outcomes.

DeepRPN-BIQA: Deep architectures with region proposal network for natural-scene and screen-content blind image quality assessment

With the emerging use of technology and screen-oriented applications in our daily life, screen content images have gained the same importance as natural scene images. This results in many natural-scene and screen-content blind image quality assessment (BIQA) models to evaluate the perceptual quality without any prior information regarding the reference image. Recently, patch-based techniques for image quality assessment (IQA) have shown promising results. As per our knowledge, no IQA technique in literature is available that can be equally effective for both natural-scene and screen-content images. In this work, we have proposed a deep architecture with a region proposal network (RPN) for blind natural-scene and screen-content image quality assessment, named DeepRPN-BIQA. The proposed architecture computes visual saliency using RPN to extract important regions having a high contribution towards the image quality. Important regions are extracted by utilizing the texture and edges of images by sliding the network over the extracted feature map from deep architectures i.e., VGGNet and ResNet. The regions proposed (RP) that overlap more than 60% are merged into one proposal and are called the region of interest (ROI). The overlap between RPs is computed using anchors having 3 different scales and aspect ratios. A local quality score is computed over each ROI and the total quality score is computed by taking the average of all the local quality scores. Experimental results show that the DeepRPN-BIQA shows a high correlation between mean observer score and predicted quality score and performs better than other models for screen content images, synthetically distorted images, images taken in real-life conditions using mobile phone cameras, and large scale image quality assessment database.

Deep multi-task learning for image/video distortions identification

Identifying distortions in images and videos is important and useful in various visual applications, such as image quality enhancement and assessment techniques. Instead of applying them blindly, these techniques can be applied or adjusted depending on the type of distortion identified. In this paper, we propose a deep multi-task learning (MTL) model for identifying the types of distortion in both images and videos, considering both single and multiple distortions. The proposed MTL model is composed of one convolutional neural network (CNN) shared between all tasks and N parallel classifiers, where each classifier is dedicated to identify a type of distortion. The proposed architecture also allows to adjust the number of tasks according to the number of distortion types considered, making the solution scalable. The proposed method has been evaluated on natural scene images and laparoscopic videos databases, each presenting a rich set of distortions. The experimental results demonstrate that our model achieves the best performance among the state-of-the-art methods for both single and multiple distortions (Code is available at: https://github.com/zoubidaameur/Deep-Multi-Task-Learning-for-Image-Video-Distortions-Identification).

Image-Abstraction Framework as a Preprocessing Technique for Extraction of Text From Underexposed Complex Background and Graphical Embossing Images

Underexposed heterogeneous complex-background and graphical embossing text documents are treated using proposed preprocessing image-abstraction framework that can deliver the effective structure preserved abstracted output by manipulating visual-features from input images. Reading of the text character in such images is extremely poor; hence, the framework effectively boosted the significant image properties and quality features at every stage. Work effectively preserves the foreground structure of an image by comprehensively integrating the sequence of NPR filters and diminishes the background content of an image, and in this way, the framework contributes to separation of foreground text from image background. Effectiveness of the proposed work has been validated by conducting the trials on the selected dataset. In addition, user's visual-feedback and image quality assessment techniques were also used to evaluate the framework. Based on the obtained abstraction output, this work extracts text-character by wisely utilizing traditional image processing techniques with an average accuracy of 98.91%.

Perceptual Image Quality Assessment Technique for Color Images based on HSI Colour Space

A new full-reference Perceptual Image Quality Assessment (PIQA) technique based on Hue-Saturation-Intensity (HSI) transformation method for colour images is offered in this work. Fundamentally, it is combined with three approaches (colour transformation, histogram processing and Human Visual System (HVS) based weighting) and it uses the Discrete Cosine Transform (DCT) domain. The PIQA is composed of four phases. At the first phase, a colour image is transformed using the HSI because an important characteristic of eyes reaction to intensity of light and colour knowledge is used for quality assessment processes. All channels' DCT coefficients have been calculated at the second phase, because many specifications cannot be assessed in the spatial domain. At the third phase, histogram based quality assessment results are obtained by using histogram of each channel (Hue, Saturation and Intensity). These results are weighted for obtaining perceptual quality result taking into account the HVS specifications at the last phase because the human eye has different sensitivities to the intensity and the others (i.e., hue and saturation). Experimental outcomes about feasibility of the PIQA on test images under different deteriorations, both sensible by the HVS and with the same Peak Signal to Noise Ratio (PSNR) result are offered. The PIQA shows better performance in comparison to state-of-the-art techniques