• Journal of Information Processing Systems
• /
• v.20 no.4
• /
• pp.558-573
• /
• 2024

Considering factors such as illumination, camera quality variations, and background-specific variations, identifying a face using a smartphone-based facial image capture application is challenging. Face Image Quality Assessment refers to the process of taking a face image as input and producing some form of "quality" estimate as an output. Typically, quality assessment techniques use deep learning methods to categorize images. The models used in deep learning are shown as black boxes. This raises the question of the trustworthiness of the models. Several explainability techniques have gained importance in building this trust. Explainability techniques provide visual evidence of the active regions within an image on which the deep learning model makes a prediction. Here, we developed a technique for reliable prediction of facial images before medical analysis and security operations. A combination of gradient-weighted class activation mapping and local interpretable model-agnostic explanations were used to explain the model. This approach has been implemented in the preselection of facial images for skin feature extraction, which is important in critical medical science applications. We demonstrate that the use of combined explanations provides better visual explanations for the model, where both the saliency map and perturbation-based explainability techniques verify predictions.

• Proceedings of the IEEK Conference
• /
• summer
• /
• pp.128-132
• /
• 2004

In this paper, we propose a new image quality assessment scheme considering the human visual perception characteristics. A subjective quality assessment is obtained by the response of the receptive field in the primary visual cortex and a human's eye can't focus on all of the visual range in a moment. Take advantage of two facts above, we apply Gabor wavelet transform, which is well fit the receptive field in the cortex, to divided constant sized subblocks. Then a local distortion of the subblocks and a global distortion for the entire image are calculated in order. The proposed method has been evaluated using video test sequences provided by the Video Quality Experts Group (VQEG). The experimental results show that good correlation with human perception is obtained using the proposed metric, which is what we called GPSNR.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.1
• /
• pp.288-307
• /
• 2016

Image distortions are typically characterized by degradations of structures. Dictionaries learned from natural images can capture the underlying structures in images, which are important for image quality assessment (IQA). This paper presents a general-purpose no-reference image quality metric using a GRadient-Induced Dictionary (GRID). A dictionary is first constructed based on gradients of natural images using K-means clustering. Then image features are extracted using the dictionary based on Euclidean-norm coding and max-pooling. A distortion classification model and several distortion-specific quality regression models are trained using the support vector machine (SVM) by combining image features with distortion types and subjective scores, respectively. To evaluate the quality of a test image, the distortion classification model is used to determine the probabilities that the image belongs to different kinds of distortions, while the regression models are used to predict the corresponding distortion-specific quality scores. Finally, an overall quality score is computed as the probability-weighted distortion-specific quality scores. The proposed metric can evaluate image quality accurately and efficiently using a small dictionary. The performance of the proposed method is verified on public image quality databases. Experimental results demonstrate that the proposed metric can generate quality scores highly consistent with human perception, and it outperforms the state-of-the-arts.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.316-320
• /
• 2009

In this paper, a reference-free perceptual quality metric is proposed for image assessment. It measures the amount of overall blockiness and blurring in the image. And edge-oriented artifacts, such as ringing, mosaic and staircase noise are also considered. In order to give a single quality score, the individual artifact scores are adaptively combined according to the difference between the edge-oriented artifacts and other artifacts. The quality score obtained by the proposed algorithm shows strong correlation with the MOS values by VQEG.

• Journal of Korean Society for Quality Management
• /
• v.49 no.1
• /
• pp.47-60
• /
• 2021

Purpose: This study proposes methods and procedures for evaluating imaging security systems quality of cabinet x-ray screening system to enhance performance certification technology. Also, conducted a comparative analysis of the literature of test-kit for imaging security quality evaluation. Methods: Comparative analysis of the test-kits and related documents for image quality assessment of cabinet x-ray screening equipment. This allows assessment items were selected and the methods for each assessment item were proposed. In addition, the configuration method of the assessment team was established by applying the technology readiness assessment(TRA). Results: Four of the assessment items were selected when estimate image quality by a comparative analysis of literature. For each assessment item, the evaluation method and minimum level of availability were determined. Finally, this paper proposes an imaging quality assessment of cabinet X-ray imaging security systems. Conclusion: Development of imaging security systems evaluation procedures for cabinet X-ray screening systems can be help improve performance certification of aviation security equipment.

• International journal of advanced smart convergence
• /
• v.1 no.1
• /
• pp.6-13
• /
• 2012

An improved algorithm for image quality assessment is presented. First a simple model of human visual system, consisting of a nonlinear function and a 2-D filter, processes the input images. This filter has one user-defined parameter, whose value depends on the reference image. This way the algorithm can adapt to different scenarios. In the next step the average value of locally computed correlation coefficients between the two processed images is found. This criterion is closely related to the way in which human observer assesses image quality. Finally, image quality measure is computed as the average value of locally computed correlation coefficients, adjusted by the average correlation coefficient between the reference and error images. By this approach the proposed measure differentiates between the random and signal dependant distortions, which have different effects on human observer. Performance of the proposed quality measure is illustrated by examples involving images with different types of degradation.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.3
• /
• pp.37-45
• /
• 2008

Quality assessment ai s to evaluate if a distorted image or video has a good quality by measuring the difference between the original and distorted images or videos. In this paper, to assess the visual qualify of a distorted image or video, visual features of the distorted image are compared with those of the original image instead of the direct comparison of the distorted image with the original image. We use edge projections from two images as features, where the edge projection can be easily obtained by projecting edge pixels in an edge map along vertical/horizontal direction. In this paper, edge projections are obtained by using vertical/horizontal directions of gradients as well as the magnitude of each gradient. Experimental results show the effectiveness of the proposed quality assessment through the comparison with conventional quality assessment algorithms such as structural similarity(SSIM), edge peak signal-to-noise ratio(EPSNR), and edge histogram descriptor(EHD) methods.

• Journal of KIISE
• /
• v.42 no.10
• /
• pp.1294-1302
• /
• 2015

A lot of image quality assessment metrics that can precisely reflect the human visual system (HVS) have previously been researched. The Structural SIMilarity (SSIM) index is a remarkable HVS-aware metric that utilizes structural information, since the HVS is sensitive to the overall structure of an image. However, SSIM fails to deal with color difference in terms of the HVS. In order to solve this problem, the Structural and Hue SIMilarity (SHSIM) index has been selected with the Hue, Saturation, Intensity (HSI) model as a color space, but it cannot reflect the HVS-aware color difference between two color images. In this paper, we propose a new image quality assessment method for a color image by using a CIE Lab color space. In addition, by using a support vector machine (SVM) classifier, we also propose an optimization system for applying optimal metric according to the types of distortion. To evaluate the proposed index, a LIVE database, which is the most well-known in the area of image quality assessment, is employed and four criteria are used. Experimental results show that the proposed index is more consistent with the other methods.

• ETRI Journal
• /
• v.44 no.1
• /
• pp.94-104
• /
• 2022

Because of its convenience and compatibility with various image processing techniques, digital image representation of holograms is generally used in digital holography, and thus, quality assessment of digital holograms is an essential issue. This study proposes a new objective quality metric for digital phase hologram image processing. The proposed metric is based on a newly defined phase distortion created by taking the 2π periodicity of phase information into account. The experimental results show that the proposed metric correlates with reconstruction image quality better than the existing metric under random distortions and also works well with JPEG 2000 compression. It is expected to be broadly used in phase image processing and compression applications including phase holograms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.5 no.9
• /
• pp.1613-1631
• /
• 2011

Several metrics have been reported in the literature to assess stereo image quality, mostly based on visual attention or human visual sensitivity based distortion prediction with the help of disparity information, which do not consider the combined aspects of human visual processing. In this paper, visual attention and depth assisted stereo image quality assessment model (VAD-SIQAM) is devised that consists of three main components, i.e., stereo attention predictor (SAP), depth variation (DV), and stereo distortion predictor (SDP). Visual attention is modeled based on entropy and inverse contrast to detect regions or objects of interest/attention. Depth variation is fused into the attention probability to account for the amount of changed depth in distorted stereo images. Finally, the stereo distortion predictor is designed by integrating distortion probability, which is based on low-level human visual system (HVS), responses into actual attention probabilities. The results show that regions of attention are detected among the visually significant distortions in the stereo image pair. Drawbacks of human visual sensitivity based picture quality metrics are alleviated by integrating visual attention and depth information. We also show that positive correlation with ground-truth attention and depth maps are increased by up to 0.949 and 0.936 in terms of the Pearson and the Spearman correlation coefficients, respectively.