Assessing Image Quality Issues for Real-World Problems

Chiu, Tai-Yin; Zhao, Yinan; Gurari, Danna

doi:10.1109/cvpr42600.2020.00370

Cited by 47 publications

(14 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Datasets need to be large enough to account for the variability between questions, images and concepts that occur in real world scenarios (Kafle & Kanan, 2017). Our work complements prior work (Chiu, Zhao, & Gurari, 2020) by offering rich, user-centered guidance in how to construct future large-scale datasets to meet the real needs of real users of VQA services, specifically people with visual impairments.…”

Section: Visual Question Answering (Vqa)mentioning

confidence: 93%

Quality of images showing medication packaging from individuals with vision impairments: Implications for the design of visual question answering applications

Davis

Xie

Gurari

2020

Proc Assoc Inf Sci Technol

Self Cite

View full text Add to dashboard Cite

Mobile phone technology empowers individuals with vision impairment to submit images with questions and promptly receive answers from remote humans through visual question answering applications. This study aimed (a) identify challenges for visually impaired users of VizWiz, a visual question answering (VQA) application, to obtain information about medication packaging and (b) recommend design guidelines for better supporting this population to receive visual assistance. Using our four‐category coding scheme, we analyzed the quality of 265 images (131 with questions; 134 without) of medication packages from VizWiz. We found that 46% of the images were legible, 40% contained clear indicators for what information was sought, 40% had minimum background clutter, and only 5% total contained sufficient information to definitively answer the users' questions. We also conducted a thematic analysis to identify major challenges in having their questions answered. Major challenges we identified include: image legibility, incomplete display of key information, and a lack of clarity on what information is being sought. We recommend designers pay more attention to how the technology can facilitate training of users on best practices and provide additional tools to aid visually impaired users in capturing good quality images that can be used to answer their questions.

show abstract

Section: Visual Question Answering (Vqa)mentioning

confidence: 93%

Quality of images showing medication packaging from individuals with vision impairments: Implications for the design of visual question answering applications

Davis

Xie

Gurari

2020

Proc Assoc Inf Sci Technol

Self Cite

View full text Add to dashboard Cite

show abstract

“…In addition, we also utilize a relevant unrecognizability prediction task, which predicts the unrecognizable degree of an image. This task is trained on the VizWiz-QualityIssues dataset (Chiu et al, 2020 ), containing images with labels of the unrecognizable degree. Even if intelligibility features of heavily distorted images cannot obtain desired results in original tasks, they can still be distinguished from features of high-quality images, which is beneficial to the IQA task.…”

Section: Proposed Methodsmentioning

confidence: 99%

IE-IQA: Intelligibility Enriched Generalizable No-Reference Image Quality Assessment

Song

Zhu

et al. 2021

Front. Neurosci.

View full text Add to dashboard Cite

Image quality assessment (IQA) for authentic distortions in the wild is challenging. Though current IQA metrics have achieved decent performance for synthetic distortions, they still cannot be satisfactorily applied to realistic distortions because of the generalization problem. Improving generalization ability is an urgent task to make IQA algorithms serviceable in real-world applications, while relevant research is still rare. Fundamentally, image quality is determined by both distortion degree and intelligibility. However, current IQA metrics mostly focus on the distortion aspect and do not fully investigate the intelligibility, which is crucial for achieving robust quality estimation. Motivated by this, this paper presents a new framework for building highly generalizable image quality model by integrating the intelligibility. We first analyze the relation between intelligibility and image quality. Then we propose a bilateral network to integrate the above two aspects of image quality. During the fusion process, feature selection strategy is further devised to avoid negative transfer. The framework not only catches the conventional distortion features but also integrates intelligibility features properly, based on which a highly generalizable no-reference image quality model is achieved. Extensive experiments are conducted based on five intelligibility tasks, and the results demonstrate that the proposed approach outperforms the state-of-the-art metrics, and the intelligibility task consistently improves metric performance and generalization ability.

show abstract

“…For example, Kang et al [7][8] proposed a multi-task shallow CNN to learn both the distortion type and the quality score; Kim and Lee [9] applied state-of-the-art FR-IQA methods to provide proxy quality scores for each image patch as the ground truth label in the pre-training stage, and the proposed network was fine-tuned by the Subjective annotations. Similarly, Da Pan et al [10] employed the U-Net to learn the local quality predicting scores previously calculated by Full-Reference IQA methods, several Dense layers were then incorporated to pool the local quality predicting scores into an overall perceptual quality score; Liang et al [11] tried to utilize similar scene as reference to provide more prior information for the IQA model; Liu et al [12] proposed to use RankNet to learn the quality rank information of image pairs in the training set, and then used the output of the second last layer to predict the quality score; Yee et al [13] tried to learn the corresponding unknown reference image from the distorted one by resorting the Generative Adversarial Networks, and to assess the perceptual quality by comparing the hallucinated reference image and the distorted image; Chiu et al [1] proposed a new IQA framework and corresponding dataset that links the IQA issue to two practical vision tasks which are image captioning and visual question answering respectively; Su et al [14] employed self-adaptive hyper network whose parameters could adjust according to image contents; Zhu et al [15] leveraged meta-learning to learn a general-purpose BIQA model from training set of several specific distortion types.…”

Section: Related Workmentioning

confidence: 99%

“…As described above, recent state-of-the-art BIQA methods focus on predicting the distorted image solely, and take less consideration on how to make their proposed models incorporated into other downstream vision tasks. Amongst the IQA works above, only [1] tries to link IQA issues with other image vision tasks. Our work exploits how to leverage IQA models to optimize the perceptual quality of multi-channel transmitting systems, which is of much importance because such work could not only optimize the transmitting system both for servers and clients but also represents a beneficial attempt for linking the gap between IQA and other image vision tasks.…”

Section: Related Workmentioning

confidence: 99%

“…Despite increasing interest has been drawn in exploiting deep convolutional neural networks (DCNN) for designing no-reference/full-reference image quality assessment (NR/FR-IQA) and notable success has achieved [1], there has largely been a disconnection between research that aimed at evaluating perceptual quality issues and research that aimed at other downstream image processing tasks [2,3]. For example, in the field of IQA, researchers always focused on how to precisely calculate the perceptual quality of images solely and somehow neglect to optimize the perceptual quality of transmitting systems in real-world based on their promising work.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Group Perceptual Quality Optimization for Multi-Channel Image Encoding Systems Based on Adaptive Hyper Networks

Chen

Chen³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Images and short videos that produced by social networks surge in recent years. Image/Video encoders, such as JPEG and H.264, are indispensably involved to reduce the transmitting bandwidth. However, based on our observation, the encoding parameters and their candidates are often preset to fixed values (or fixed candidate values) in real-world scenarios, which might not be the optimal bandwidth allocation strategy. Considering that, we propose an efficient group quality optimization (GQO) framework for multichannel image/video encoding systems in which the encoding parameters are configured in a perceptualquality-driven manner. The GQO framework employs adaptive hyper network to predict the relationships between encoding parameters, transmitting resources, and perceptual qualities, i.e., just taking the pristine image as input, the adaptive hyper network could accurately yield a global overview of perceptual quality and transmitting resource varied along encoding parameters. A step-by-step optimization procedure is then employed to search the optimal encoding parameter for each channel so that overall perceptual quality could be maximized under limited transmitting resource. Experimental results demonstrate the proposed GQO framework could achieve higher perceptual quality whilst maintain the same bandwidth compared to traditional allocation strategies where encoding parameters are preset.

show abstract

Assessing Image Quality Issues for Real-World Problems

Cited by 47 publications

References 48 publications

Quality of images showing medication packaging from individuals with vision impairments: Implications for the design of visual question answering applications

Quality of images showing medication packaging from individuals with vision impairments: Implications for the design of visual question answering applications

IE-IQA: Intelligibility Enriched Generalizable No-Reference Image Quality Assessment

Group Perceptual Quality Optimization for Multi-Channel Image Encoding Systems Based on Adaptive Hyper Networks

Contact Info

Product

Resources

About