IEEE Transactions on Image Processing最新文献_第10页

Stacked Deconvolutional Network for Semantic Segmentation. 用于语义分割的堆叠去卷积网络

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2019-01-25 DOI: 10.1109/TIP.2019.2895460

Jun Fu, Jing Liu, Yuhang Wang, Jin Zhou, Changyong Wang, Hanqing Lu

引用次数: 0

Monocular Depth Estimation with Augmented Ordinal Depth Relationships. 利用增量正序深度关系进行单目深度估算

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2018-10-24 DOI: 10.1109/TIP.2018.2877944

Yuanzhouhan Cao, Tianqi Zhao, Ke Xian, Chunhua Shen, Zhiguo Cao, Shugong Xu

{"title":"Monocular Depth Estimation with Augmented Ordinal Depth Relationships.","authors":"Yuanzhouhan Cao, Tianqi Zhao, Ke Xian, Chunhua Shen, Zhiguo Cao, Shugong Xu","doi":"10.1109/TIP.2018.2877944","DOIUrl":"10.1109/TIP.2018.2877944","url":null,"abstract":"Most existing algorithms for depth estimation from single monocular images need large quantities of metric groundtruth depths for supervised learning. We show that relative depth can be an informative cue for metric depth estimation and can be easily obtained from vast stereo videos. Acquiring metric depths from stereo videos is sometimes impracticable due to the absence of camera parameters. In this paper, we propose to improve the performance of metric depth estimation with relative depths collected from stereo movie videos using existing stereo matching algorithm.We introduce a new \"Relative Depth in Stereo\" (RDIS) dataset densely labelled with relative depths. We first pretrain a ResNet model on our RDIS dataset. Then we finetune the model on RGB-D datasets with metric ground-truth depths. During our finetuning, we formulate depth estimation as a classification task. This re-formulation scheme enables us to obtain the confidence of a depth prediction in the form of probability distribution. With this confidence, we propose an information gain loss to make use of the predictions that are close to ground-truth. We evaluate our approach on both indoor and outdoor benchmark RGB-D datasets and achieve state-of-the-art performance.","PeriodicalId":13217,"journal":{"name":"IEEE Transactions on Image Processing","volume":" ","pages":""},"PeriodicalIF":10.6,"publicationDate":"2018-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"36624481","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deep Active Learning with Contaminated Tags for Image Aesthetics Assessment. 使用污染标签进行图像美学评估的深度主动学习

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2018-04-18 DOI: 10.1109/TIP.2018.2828326

Zhenguang Liu, Zepeng Wang, Yiyang Yao, Luming Zhang, Ling Shao

{"title":"Deep Active Learning with Contaminated Tags for Image Aesthetics Assessment.","authors":"Zhenguang Liu, Zepeng Wang, Yiyang Yao, Luming Zhang, Ling Shao","doi":"10.1109/TIP.2018.2828326","DOIUrl":"10.1109/TIP.2018.2828326","url":null,"abstract":"Image aesthetic quality assessment has becoming an indispensable technique that facilitates a variety of image applications, e.g., photo retargeting and non-realistic rendering. Conventional approaches suffer from the following limitations: 1) the inefficiency of semantically describing images due to the inherent tag noise and incompletion, 2) the difficulty of accurately reflecting how humans actively perceive various regions inside each image, and 3) the challenge of incorporating the aesthetic experiences of multiple users. To solve these problems, we propose a novel semi-supervised deep active learning (SDAL) algorithm, which discovers how humans perceive semantically important regions from a large quantity of images partially assigned with contaminated tags. More specifically, as humans usually attend to the foreground objects before understanding them, we extract a succinct set of BING (binarized normed gradients) [60]-based object patches from each image. To simulate human visual perception, we propose SDAL which hierarchically learns human gaze shifting path (GSP) by sequentially linking semantically important object patches from each scenery. Noticeably, SDLA unifies the semantically important regions discovery and deep GSP feature learning into a principled framework, wherein only a small proportion of tagged images are adopted. Moreover, based on the sparsity penalty, SDLA can optimally abandon the noisy or redundant low-level image features. Finally, by leveraging the deeply-learned GSP features, a probabilistic model is developed for image aesthetics assessment, where the experience of multiple professional photographers can be encoded. Besides, auxiliary quality-related features can be conveniently integrated into our probabilistic model. Comprehensive experiments on a series of benchmark image sets have demonstrated the superiority of our method. As a byproduct, eye tracking experiments have shown that GSPs generated by our SDAL are about 93% consistent with real human gaze shifting paths.","PeriodicalId":13217,"journal":{"name":"IEEE Transactions on Image Processing","volume":" ","pages":""},"PeriodicalIF":10.6,"publicationDate":"2018-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"36302732","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Digital affine shear filter banks with 2-layer structure 两层结构的数字仿射剪切滤波器组

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2017-07-01 DOI: 10.1109/SAMPTA.2017.8024369

Zhihua Che, X. Zhuang

引用次数: 6

Improved Denoising via Poisson Mixture Modeling of Image Sensor Noise 基于泊松混合模型的图像传感器噪声改进去噪

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2017-04-01 DOI: 10.1109/TIP.2017.2651365

Jiachao Zhang, Keigo Hirakawa

引用次数: 32

Non-Additive Imprecise Image Super-Resolution in a Semi-Blind Context 半盲环境下的非加性不精确图像超分辨率

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2017-03-01 DOI: 10.1109/TIP.2016.2621414

Fares Graba, F. Comby, O. Strauss

引用次数: 9

Bayesian Contrast Measures and Clutter Distribution Determinants of Human Target Detection 人体目标检测中的贝叶斯对比度量和杂波分布决定因素

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2017-03-01 DOI: 10.1109/TIP.2016.2644269

A. Novak, N. Armstrong, T. Caelli, Iain Blair

{"title":"Bayesian Contrast Measures and Clutter Distribution Determinants of Human Target Detection","authors":"A. Novak, N. Armstrong, T. Caelli, Iain Blair","doi":"10.1109/TIP.2016.2644269","DOIUrl":"https://doi.org/10.1109/TIP.2016.2644269","url":null,"abstract":"Human target detection is known to be dependent on a number of components: one, basic electro-optics including image contrast, the target size, pixel resolution, and contrast sensitivity; two, target shape, image type and features, types of clutter; and three, context and task requirements. Here, we consider a Bayesian approach to investigating how these components contribute to target detection. To this end, we develop and compare three different formulations for contrast: mean contrast, perceptual contrast, and a Bayesian-based histogram contrast statistic. Results on past detection data show how the latter contrast measure correlates well with human performance factoring out all other dimensions. As for clutter, our findings show that with large targets, there are effectively no clutter effects. Furthermore, clutter does not have a major effect on detection when it is not contiguous with the target even when it is smaller. However, except for large targets, when the target is contiguous with the clutter, detection clearly decreases as a function of the similarity of target and clutter features—creating type of “clutter camouflage”. This Bayesian formulation uses priors based on the contrast histogram statistics derived from all the images, the image context, and implies that human observers have adapted their criteria to fit with the image set, context, and task.","PeriodicalId":13217,"journal":{"name":"IEEE Transactions on Image Processing","volume":"26 1","pages":"1115-1126"},"PeriodicalIF":10.6,"publicationDate":"2017-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TIP.2016.2644269","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62581026","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Waterloo Exploration Database: New Challenges for Image Quality Assessment Models 滑铁卢探索数据库:图像质量评估模型的新挑战

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2017-02-01 DOI: 10.1109/TIP.2016.2631888

Kede Ma, Zhengfang Duanmu, Q. Wu, Zhou Wang, Hongwei Yong, Hongliang Li, Lei Zhang

{"title":"Waterloo Exploration Database: New Challenges for Image Quality Assessment Models","authors":"Kede Ma, Zhengfang Duanmu, Q. Wu, Zhou Wang, Hongwei Yong, Hongliang Li, Lei Zhang","doi":"10.1109/TIP.2016.2631888","DOIUrl":"https://doi.org/10.1109/TIP.2016.2631888","url":null,"abstract":"The great content diversity of real-world digital images poses a grand challenge to image quality assessment (IQA) models, which are traditionally designed and validated on a handful of commonly used IQA databases with very limited content variation. To test the generalization capability and to facilitate the wide usage of IQA techniques in real-world applications, we establish a large-scale database named the Waterloo Exploration Database, which in its current state contains 4744 pristine natural images and 94 880 distorted images created from them. Instead of collecting the mean opinion score for each image via subjective testing, which is extremely difficult if not impossible, we present three alternative test criteria to evaluate the performance of IQA models, namely, the pristine/distorted image discriminability test, the listwise ranking consistency test, and the pairwise preference consistency test (P-test). We compare 20 well-known IQA models using the proposed criteria, which not only provide a stronger test in a more challenging testing environment for existing models, but also demonstrate the additional benefits of using the proposed database. For example, in the P-test, even for the best performing no-reference IQA model, more than 6 million failure cases against the model are “discovered” automatically out of over 1 billion test pairs. Furthermore, we discuss how the new database may be exploited using innovative approaches in the future, to reveal the weaknesses of existing IQA models, to provide insights on how to improve the models, and to shed light on how the next-generation IQA models may be developed. The database and codes are made publicly available at: https://ece.uwaterloo.ca/~k29ma/exploration/.","PeriodicalId":13217,"journal":{"name":"IEEE Transactions on Image Processing","volume":"26 1","pages":"1004-1016"},"PeriodicalIF":10.6,"publicationDate":"2017-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TIP.2016.2631888","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62578720","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 459

A New Intrinsic-Lighting Color Space for Daytime Outdoor Images 一种新的白天户外图像的内在照明色彩空间

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2017-02-01 DOI: 10.1109/TIP.2016.2642788

Zhi Han, Jiandong Tian, Liangqiong Qu, Yandong Tang

引用次数: 6

ORGM: Occlusion Relational Graphical Model for Human Pose Estimation 人体姿态估计的遮挡关系图形模型

IF 10.6 1区计算机科学

IEEE Transactions on Image Processing Pub Date : 2017-02-01 DOI: 10.1109/TIP.2016.2639441

Lianrui Fu, Junge Zhang, Kaiqi Huang

引用次数: 20