Earticle

This paper presents a method for accurate camera self-calibration based on SIFT Feature Detection and image quality assessment. We performed image quality assessment to select high quality images for the camera self-calibration process. We defined high quality images as those that contain little or no blur, and have maximum contrast among images captured within a short period. The image quality assessment includes blur detection and contrast assessment. Blur detection is based on the statistical analysis of energy and standard deviation of high frequency components of the images using Discrete Cosine Transform. Contrast assessment is based on contrast measurement and selection of the high contrast images among some images captured in a short period. Experimental results show little or no distortion in the perspective view of the images. Thus, the suggested method achieves camera self-calibration accuracy of approximately 93%.

대조도가 강화된 CT에서는 칼슘을 관찰하기 위해 윈도우 설정을 통한 듀얼 에너지 테스트 후 조건 결정을 통해 물질을 관찰할 수 있다. 따라서 CT에서는 듀얼 에너지 테스트 후 수행된 후보 결정은 80kVp 및 140 kVp의 에너지에 대한 비율을 통해 이미지 판별력이 형성된다. 이번 연구에서는 CT영상의 대조도 강화 조건에서 0.3 ~ 0.5 g의 칼슘을 주사기 에 주입한 후, SECT의 120 kVp + 200 mAs에 초점을 맞춰 DECT + AEC, DECT + 200 mAs, DECT + 300 mAs, DECT_400mAs로 선량을 변경하여 선량과 영상 품질의 변화를 관찰하여 대조 강화 주사기에서 칼슘의 최소 판별력에 대한 mAs의 에너지 가중치와 값을 얻었다. 선량의 DLP는 SECT의 경우 72 mGy, DECT+AEC의 경우 74 mGy, DECT + 400 mAs의 경우 91 mGy, DECT + 300 mAs의 경우 68 mGy, DE + 200 mAs의 경우 46 mGy의 결과를 얻었다. SECT에 따른 SNR 차이는 SECT – DE AEC의 경우 0.33 ± 0.19, SECT-DE 400 mAs의 경우 0.43 ± 0.26, SECT-DE 200 mAs의 경우 0.22 ± 0.21로 모두 유의한 차이를 보였다. SECT에 따른 CNR 차이는 SECT-DE 400 mAs의 경우 0.062 ± 0.22, SECT-DE 300 mAs의 경우 0.036 ± 0.35, SECT-DE 300 mAs의 경우 0.092 ± 0.27, SECT-DE 200 mAs의 경우 0.490 ± 0.28로 모두 유의한 차이를 보였다.

For the observation of calcium in contrast-enhanced CT, it can be observed through candidate crystals after window setting or dual energy tests. The candidate crystals performed after the Dual energy test generate image discrimination power through the ratio to the energy of the 80 and 140 kVp. In this study, 0.3 ~ 0.5g of calcium was inserted into a syringe under contrast-enhanced conditions, and then the dose was changed to DECT+AEC, DECT+200mAs, DECT+300mAs, and DECT_400mAs, focusing on SECT's 120kVp+200mAs, to observe changes in the dose and image quality of images to obtain energy weights and values of mAs for the minimum discrimination power of calcium in the contrast-enhanced syringe.. The DLP of the dose is 72 mGy for SECT, 74 mGy for DECT + AEC, 91 mGy for DECT + 400 mAs, 68 mGy for DECT + 300 mAs, and 46 mGy for DE + 200 mAs. The difference in SNR based on SECT is that SECT – 0.33±0.19 for DE AEC, 0.43±0.26 for SECT-DE 400 mAs, 0.22±0.21 for SECT-DE 200 mAs, all of which showed significant differences. The difference in CNR based on SECT was 0.062±0.22 for SECT-DE 400 mAs, 0.036±0.35 for SECT-DE 300 mAs, 0.092±0.27 for SECT-DE 300 mAs, and 0.490±0.28 for SECT-DE 200 mAs, all of which showed significant differences.

최근 얼굴인식 연구에서는 이미지 품질을 고려하여 낮은 품질의 이미지에 대해서 알고리즘 성능을 개선 하고 있다. 이러한 연구에서 사용하는 이미지 품질의 조작적 정의는 샘플의 모델 임베딩 값의 L2 노름 (특징 정규화)을 사용하고 있으며, 얼굴인식 외의 연구인 Out Of Distribution(OOD)에서 특징 정규화는 이미 지 품질이 아닌, 학습 데이터셋의 분포와 차이나는 데이터를 구별하기 위해 사용되고 있다. 이는 특징 정 규화가 모델에 학습된 데이터에 따라 달라짐을 시사한다. 얼굴인식 학습 데이터 셋은 대부분 롱 테일 분 포를 가지고 있기에, 본 연구는 이를 고려하여 특징 정규화를 클래스 별로 표준화하여 전처리를 한 결과 특징 정규화와 이미지 품질의 상관관계가 더 높아진 결과를 보여준다. 추후 얼굴인식 분야에서는 데이터 셋의 분포를 고려하여 특징 정규화를 이미지 품질로 사용할 것을 제안한다.

Image quality assessment (IQA) is crucial in image processing algorithms. In the state-of-the-art IQA index, the structural similarity (SSIM) index has been proved to be better objective quality assessment metric. However, the accuracy of SSIM is relatively lacking when used to access blurred images. And the component weights of structural similarity (SSIM) index are fixed in some past environments. So an improved assessment algorithm incorporating multiple linear regressions and SSIM index was proposed in this paper. We use regression analysis to adjust the component weight of SSIM index. So the improved algorithm is more accuracy on different distortion types’ quality assessment. Experimental results show that the improved SSIM algorithm is better than traditional methods in nonlinear regression correlation coefficient, Spearman correlation coefficient and out ratio.

A novel objective quality assessment method is proposed for super-resolution images in this manuscript. We not only estimate the preserved information of each spatial location in the super-resolution image by structural similarity, but also compute the local phase coherence (LPC) with which we can detect the image blur in the super-resolution image. After the preserved structural information and blur information is obtained, an overall evaluation of visual quality of the super-resolution image can be computed. Experimental results show that the proposed objective quality assessment method can be used in the real applications with the original high-resolution images unavailable.

Many researchers evaluate images by objective image quality assessments instead of subjective ones. Objective image quality assessment sets up mathematical model according to the human visual system, and it evaluates the image quality through the reference image and the distorted image. The Structural Similarity Index (SSIM) is one of the most classical methods in image quality assessment. However, SSIM has several inherent shortcomings. First, SSIM does not take spatial position, spatial frequency, or direction into account. Second, SSIM considers that different regions in an image have equal importance for overall image quality assessment. Third, it is unreasonable to use fixed parameters for various images. To overcome these shortcomings, we propose a new method of image quality assessment based on Nonsubsampled Contourlet Transform (NSCT). Firstly, NSCT is performed to decompose the image into a low-pass map and high-pass ones. Then, low-pass and high-pass maps are respectively assessed with different strategies. In addition, saliency map is added to describe the importance of different regions in an image. Last, we proposed an approach to calculate the adaptive parameters for various images. Experimental comparisons among five public benchmark databases demonstrate that the proposed method is better than other competing methods.

Due to the existing image quality assessment algorithm does not take the visual information and the essential features of the image into account and cannot meet the actual need, a new method of objective quality assessment which related to both cases was proposed in this paper. The singular value information of the image shows the essential information of image and human eyes are sensitive to the edge information of image. Theoretically, the algorithm of image quality assessment based on edge information and Singular Value Decomposition is better than traditional methods. The simulation experiment results show the proposed algorithm is more consistent with human subject scores and has greater stability than traditional methods. Through comparison with the time efficiency, the proposed algorithm can basically be able to meet the practical demand, and the algorithm is more usability.

The main drawback of the phase congruency feature employed in the feature similarity index (FSIM) image quality assessment (IQA) algorithm is its low computational efficiency. In this paper, a novel fast feature similarity index (FFSIM) for image quality assessment is proposed. Based on the fact that human visual system (HVS) responds to the brightness stimulus mainly complying with Weber's law, the proposed FFSIM only performs spatial filtering to quickly calculate the contrast between the current pixel and its background, which is used to compute Weber visual salience similarity and a weighting coefficient in pooling stage after applied nonlinear mapping. Weber contrast and the gradient magnitude play complementary roles in characterizing the image local quality. After obtaining the local quality map, we use Weber weighting coefficient again as a weighting coefficient to derive a single quality score. As such, the multi-scale version of the FFSIM algorithm, i.e., MS-FFSIM is also proposed, which complies with the spatial frequency response characteristics of the HVS system. Extensive experiments performed on six publicly available IQA databases demonstrate that the proposed FFSIM and MS-FFSIM can achieve higher consistency with the subjective evaluations than state-of-the-art IQA metrics and the computational efficiency is greatly improved as well.

Purpose: To determine the impact of an image processing technique on diagnostic accuracy of digital panoramic radiographs for the assessment of anatomical structures in paediatric patients with mixed dentition. Materials and Methods: The study consisted of 50 digital panoramic radiographs of children aged from 6 to 12 years, which were later on processed using a dedicated image processing method. A modified clinical image quality evaluation chart was used to evaluate the diagnostic accuracy of anatomical structures in maxillary and mandibular anterior and maxillary premolar region of processed images. Results: A statistically significant difference was observed between pre and post-processed evaluation of anatomical structures(P<0.05) in the maxillary and mandibular anterior region. The anterior region was found to be more accurate in post-processed images. No significant difference was observed in the maxillary premolar region (P>0.05). The Inter-observer and intra-observer reliability of both pre and post processed images were excellent (>0.82) for anterior region and good (>0.63) for premolar region. Conclusion: The application of image processing technique in digital panoramic radiography can be considered a reliable method for improving the quality of anatomical structures in paediatric patients with mixed dentition.

Multimedia is a ubiquitous and indispensable part of our daily life and learning such as audio, image, and video. Objective and subjective quality evaluations play an important role in various multimedia applications. Blind image quality assessment (BIQA) is used to indicate the perceptual quality of a distorted image, while its reference image is not considered and used. Blur is one of the common image distortions. In this paper, we propose a novel BIQA index for Gaussian blur distortion based on the fact that images with different blur degree will have different changes through the same blur. We describe this discrimination from three aspects: color, edge, and structure. For color, we adopt color histogram; for edge, we use edge intensity map, and saliency map is used as the weighting function to be consistent with human visual system (HVS); for structure, we use structure tensor and structural similarity (SSIM) index. Numerous experiments based on four benchmark databases show that our proposed index is highly consistent with the subjective quality assessment.

We propose a new method that specifies objective image quality factors by evaluating an image quality measurement model using random images. In other words, No-Reference variables are used to evaluate the quality of an original image without using any reference for comparison. 1000 portrait images were collected from a web gallery with votes constituting over 30 recommendation values. The bottom-up data collecting process was used to calculate the following image quality factors: total range, average, standard deviation, normalized distribution, z-score, preference percentage. A final grade is awarded out of 100 points, and this method ranks and grades the final estimated image quality preference in terms of total image quality factors. The results of the proposed image quality evaluation model consist of the specific dynamic range, skin tone R, G, B, L, A, B, and RSC contrast. We can present the total for the expected preference points as the average of the objective image qualities. Our proposed image quality evaluation model can measure the preferences for an actual image using a statistical analysis. The results indicate that this is a practical image quality measurement model that can extract a subject's preferred image quality.

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.

본 논문에서는 기존에 영상의 품질을 평가하는 데 사용되던 지표가 저조도 영상에 대해서도 적용될 수 있음을 확인한다. 저조도 영상의 특성상, 빛과 관련된 요인들이 다양한 잡음 패턴을 만들어내고 빛의 양이 적을수록 극심한 잡음을 가지고 있다. 그렇기 때문에, 잡음이 없는 깨끗한 영상을 구하기 힘든 상황에서 잡음이 제거된 저조도 영상의 품질을 사람의 눈으로 판단하는 경우가 많다. 본 논문에서는, ground truth를 구할 수 없는 저조도 영상의 잡음을 Noise2Noise를 이용해서 제거하고, MTF와 SNR 등의 지표로 공간 해상도와 방사 해상도를 ISO 12233 차트와 colorchecker를 대상으로 평가한다. 정성적 평가 위주로 평가되던 저조도 영상의 품질이 정량적으로도 평가될 수 있음을 보여줄 수 있다.

In this paper, it is confirmed that the metrics used to evaluate image quality can be applied to low-light images. Due to the nature of low-illumination images, factors related to light create various noise patterns, and the smaller the amount of light, the more severe the noise. Therefore, in situations where it is difficult to obtain a clean image without noise, the quality of a low-illuminance image from which noise has been removed is often judged by the human eye. In this paper, noise in low-illuminance images for which ground truth cannot be obtained is removed using Noise2Noise, and spatial resolution and radial resolution are evaluated using ISO 12233 charts and colorchecker as metrics such as MTF and SNR. It can be shown that the quality of the low-illuminance image, which has been evaluated mainly for qualitative evaluation, can also be evaluated quantitatively.

This paper presents a method for accurate camera self-calibration based on SIFT Feature Detection and image quality assessment. We performed image quality assessment to select high quality images for the camera self-calibration process. We defined high quality images as those that contain little or no blur, and have maximum contrast among images captured within a short period. The image quality assessment includes blur detection and contrast assessment. Blur detection is based on the statistical analysis of energy and standard deviation of high frequency components of the images using Discrete Cosine Transform. Contrast assessment is based on contrast measurement and selection of the high contrast images among some images captured in a short period. Experimental results show little or no distortion in the perspective view of the images. Thus, the suggested method achieves camera self-calibration accuracy of approximately 93%.

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.

Purpose: The purpose of this study was to apply a newly developed free software program, at low cost and with minimal time, to evaluate the quality of dental and maxillofacial cone-beam computed tomography (CBCT) images. Materials and Methods: A polymethyl methacrylate (PMMA) phantom, CQP-IFBA, was scanned in 3 CBCT units with 7 protocols. A macro program was developed, using the free software ImageJ, to automatically evaluate the image quality parameters. The image quality evaluation was based on 8 parameters: uniformity, the signal-to-noise ratio (SNR), noise, the contrast-to-noise ratio (CNR), spatial resolution, the artifact index, geometric accuracy, and low-contrast resolution. Results: The image uniformity and noise depended on the protocol that was applied. Regarding the CNR, high-density structures were more sensitive to the effect of scanning parameters. There were no significant differences between SNR and CNR in centered and peripheral objects. The geometric accuracy assessment showed that all the distance measurements were lower than the real values. Low-contrast resolution was influenced by the scanning parameters, and the 1-mm rod present in the phantom was not depicted in any of the 3 CBCT units. Smaller voxel sizes presented higher spatial resolution. There were no significant differences among the protocols regarding artifact presence. Conclusion: This software package provided a fast, low-cost, and feasible method for the evaluation of image quality parameters in CBCT.

Purpose: To compare image quality in selective intracoronary contrast-injected computed tomography angiography (SelectiveCTA) with that in conventional intravenous contrast-injected CTA (IV-CTA). Materials and Methods: Six pigs (35 to 40 kg) underwent both IV-CTA using an intravenous injection (60 mL) and Selective-CTA using an intracoronary injection (20 mL) through a guide-wire during/after percutaneous coronary intervention. Images of the common coronary artery were acquired. Scans were performed using a combined machine comprising an invasive coronary angiography suite and a 320-channel multi-slice CT scanner. Quantitative image quality parameters of CT attenuation, image noise, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), mean lumen diameter (MLD), and mean lumen area (MLA) were measured and compared. Qualitative analysis was performed using intraclass correlation coefficient (ICC), which was calculated for analysis of interobserver agreement. Results: Quantitative image quality, determined by assessing the uniformity of CT attenuation (399.06 vs. 330.21, p<0.001), image noise (24.93 vs. 18.43, p<0.001), SNR (16.43 vs. 18.52, p=0.005), and CNR (11.56 vs. 13.46, p=0.002), differed significantly between IV-CTA and Selective-CTA. MLD and MLA showed no significant difference overall (2.38 vs. 2.44, p=0.068, 4.72 vs. 4.95, p=0.078). The density of contrast agent was significantly lower for selective-CTA (13.13 mg/mL) than for IV-CTA (400 mg/mL). Agreement between observers was acceptable (ICC=0.79±0.08). Conclusion: Our feasibility study in swine showed that compared to IV-CTA, Selective-CTA provides better image quality and requires less iodine contrast medium

본 연구는 CR영상에서 선량이 화질에 미치는 영향을 평가하기위해 수행되었다. 본 연구의 궁극적인 목적은 임상 흉부진단에 필요한 영상화질을 얻을 수 있는 최적 선량을 찾는 것이다. 영상화질 평가를 위해서 다양한 선량에서의 MTF, NNPS, 그리고 NEQ를 측정하였으며, MTF 측정과 실험장치 구성은 International Electrotechnical Commission(IEC)에서 제시한 절차에 따라 수행하였다. 실험 결과를 통해 흉부진단의 경우 자동노출조절 (Automatic Exposure Control, AEC) 제어반에서 자동으로 설정해주는 선량의 절반 선량으로도 필요한 영상화질이 얻어짐을 알 수 있었다. 본 연구를 통해 AEC에서 제시하는 선량이 최적 선량이 아니며 화질평가를 통해서 얻어진 최적 선량을 사용하면 환자의 피폭을 상당량 줄일 수 있음을 보였다.

This research was accomplished to assess dose effects on image quality at computed radiography (CR). The ultimate target of the research was finding optimized exposure that provides necessary image quality for the clinical chest diagnosis. Modulation transfer function (MTF), normalized noise power spectrum (NNPS), and Noise equivalent quanta (NEQ) corresponding to the different doses were measured for the assessment of image quality. The preparation of "edge test device" used in MTF measurement and experimental geometry setup were followed by the recommendations of International Electrotechnical Commission (IEC). The experimental results show the necessary image quality can be achieved even at a half of the automatic exposure control (AEC) setting dose for chest diagnosis. It means that the patient exposure can be reduced dramatically by using optimized dose.