2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA)最新文献_第7页

Smooth Globally Warp Locally: Video Stabilization Using Homography Fields 平滑全局局部扭曲:视频稳定使用单应性领域

2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA) Pub Date : 2015-11-01 DOI: 10.1109/DICTA.2015.7371309

William X. Liu, Tat-Jun Chin

{"title":"Smooth Globally Warp Locally: Video Stabilization Using Homography Fields","authors":"William X. Liu, Tat-Jun Chin","doi":"10.1109/DICTA.2015.7371309","DOIUrl":"https://doi.org/10.1109/DICTA.2015.7371309","url":null,"abstract":"Conceptually, video stabilization is achieved by estimating the camera trajectory throughout the video and then smoothing the trajectory. In practice, the pipeline invariably leads to estimating update transforms that adjust each frame of the video such that the overall sequence appears to be stabilized. Therefore, we argue that estimating good update transforms is more critical to success than accurately modeling and characterizing the motion of the camera. Based on this observation, we propose the usage of homography fields for video stabilization. A homography field is a spatially varying warp that is regularized to be as projective as possible, so as to enable accurate warping while adhering closely to the underlying geometric constraints. We show that homography fields are powerful enough to meet the various warping needs of video stabilization, not just in the core step of stabilization, but also in video inpainting. This enables relatively simple algorithms to be used for motion modeling and smoothing. We demonstrate the merits of our video stabilization pipeline on various public testing videos.","PeriodicalId":214897,"journal":{"name":"2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121523491","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 7

A Multi-Kernel Local Level Set Image Segmentation Algorithm for Fluorescence Microscopy Images 荧光显微图像的多核局部水平集分割算法

2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA) Pub Date : 2015-11-01 DOI: 10.1109/DICTA.2015.7371218

A. Gharipour, Alan Wee-Chung Liew

引用次数: 1

Video Classification Based on Spatial Gradient and Optical Flow Descriptors 基于空间梯度和光流描述子的视频分类

2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA) Pub Date : 2015-11-01 DOI: 10.1109/DICTA.2015.7371319

Xiaolin Tang, A. Bouzerdoum, S. L. Phung

{"title":"Video Classification Based on Spatial Gradient and Optical Flow Descriptors","authors":"Xiaolin Tang, A. Bouzerdoum, S. L. Phung","doi":"10.1109/DICTA.2015.7371319","DOIUrl":"https://doi.org/10.1109/DICTA.2015.7371319","url":null,"abstract":"Feature point detection and local feature extraction are the two critical steps in trajectory-based methods for video classification. This paper proposes to detect trajectories by tracking the spatiotemporal feature points in salient regions instead of the entire frame. This strategy significantly reduces noisy feature points in the background region, and leads to lower computational cost and higher discriminative power of the feature set. Two new spatiotemporal descriptors, namely the STOH and RISTOH are proposed to describe the spatiotemporal characteristics of the moving object. The proposed method for feature point detection and local feature extraction is applied for human action recognition. It is evaluated on three video datasets: KTH, YouTube, and Hollywood2. The results show that the proposed method achieves a higher classification rate, even when it uses only half the number of feature points compared to the dense sampling approach. Moreover, features extracted from the curvature of the motion surface are more discriminative than features extracted from the spatial gradient.","PeriodicalId":214897,"journal":{"name":"2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA)","volume":"6 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116817338","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Face Recognition Using Two-Dimensional Tunable-Q Wavelet Transform 基于二维可调q小波变换的人脸识别

2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA) Pub Date : 2015-11-01 DOI: 10.1109/DICTA.2015.7371261

T. S. Kumar, Vivek Kanhangad

引用次数: 3

Improved Classification and Reconstruction by Introducing Independence and Randomization in Deep Neural Networks 在深度神经网络中引入独立性和随机化改进分类和重构

2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA) Pub Date : 2015-11-01 DOI: 10.1109/DICTA.2015.7371270

G. Hiranandani, H. Karnick

{"title":"Improved Classification and Reconstruction by Introducing Independence and Randomization in Deep Neural Networks","authors":"G. Hiranandani, H. Karnick","doi":"10.1109/DICTA.2015.7371270","DOIUrl":"https://doi.org/10.1109/DICTA.2015.7371270","url":null,"abstract":"This paper deals with a novel way of improving classification as well as reconstructions obtained from deep neural networks. The underlying ideas that have been used throughout are Independence and Randomization. The idea is to expose the inherent properties of neural network architectures and to make simpler models that are easy to implement rather than creating highly fine-tuned and complex neural network architectures. For the most basic type of deep neural network i.e. fully connected, it has been shown that dividing the data into independent components and training each component separately not only reduces the parameters to be learned but also the training is more efficient. And if the predictions are fused appropriately the overall accuracy also increases. Using the orthogonality of LAB colour space, it is shown that L,A and B components trained separately produce better reconstructions than RGB components taken together which in turn produce better reconstructions than LAB components taken together. Based on a similar approach, randomization has been injected into the networks so as to make different networks as independent as possible. Again fusing predictions appropriately increases accuracy. The best error on MNIST's test data set was 1.91% which is a drop by 1.05% in comparison to architectures that we created similar to [1]. As the technique is architecture independent it can be applied to other networks - for example CNNs or RNNs.","PeriodicalId":214897,"journal":{"name":"2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125744766","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Linear Complexity Approximate Method for Multi-Target Particle Filter Track before Detect 多目标粒子滤波检测前跟踪的线性复杂度近似方法

2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA) Pub Date : 2015-11-01 DOI: 10.1109/DICTA.2015.7371215

S. Davey, B. Cheung

引用次数: 1

Localized Deep Extreme Learning Machines for Efficient RGB-D Object Recognition 高效RGB-D对象识别的局部深度极限学习机

2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA) Pub Date : 2015-11-01 DOI: 10.1109/DICTA.2015.7371280

H. F. Zaki, F. Shafait, A. Mian

{"title":"Localized Deep Extreme Learning Machines for Efficient RGB-D Object Recognition","authors":"H. F. Zaki, F. Shafait, A. Mian","doi":"10.1109/DICTA.2015.7371280","DOIUrl":"https://doi.org/10.1109/DICTA.2015.7371280","url":null,"abstract":"Existing RGB-D object recognition methods either use channel specific handcrafted features, or learn features with deep networks. The former lack representation ability while the latter require large amounts of training data and learning time. In real-time robotics applications involving RGB-D sensors, we do not have the luxury of both. In this paper, we propose Localized Deep Extreme Learning Machines (LDELM) that efficiently learn features from RGB-D data. By using localized patches, not only is the problem of data sparsity solved, but the learned features are robust to occlusions and viewpoint variations. LDELM learns deep localized features in an unsupervised way from random patches of the training data. Each image is then feed-forwarded, patch-wise, through the LDELM to form a cuboid of features. The cuboid is divided into cells and pooled to get the final compact image representation which is then used to train an ELM classifier. Experiments on the benchmark Washington RGB-D and 2D3D datasets show that the proposed algorithm not only is significantly faster to train but also outperforms state-of-the-art methods in terms of accuracy and classification time.","PeriodicalId":214897,"journal":{"name":"2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133401363","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 9

Automatic Diagnosis Support System Using Nuclear and Luminal Features 基于核和腔特征的自动诊断支持系统

2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA) Pub Date : 2015-11-01 DOI: 10.1109/DICTA.2015.7371235

Yuriko Harai, Toshiyuki Tanaka

{"title":"Automatic Diagnosis Support System Using Nuclear and Luminal Features","authors":"Yuriko Harai, Toshiyuki Tanaka","doi":"10.1109/DICTA.2015.7371235","DOIUrl":"https://doi.org/10.1109/DICTA.2015.7371235","url":null,"abstract":"We present a method of automatic colorectal cancer diagnosis that can quantify cellular and structural tissue information. In this paper, we consider sixteen-dimensional features, consisting of the nuclei-cytoplasm (NC) ratio, connected nuclei area, and atypical lumen ratio. For the purpose of imitating the conditions of accurate medical diagnosing, we introduce a four-class classification for group 1, group 3 low, group 3 high, and group 5 biopsies (group 5 biopsies include well-, moderately, and poorly differentiated) in contrast to most previous works proposed in the literature, which classify biopsies into two or three classes. The image set used in this paper consists of 400 images stained from 123 patients by hematoxylin and eosin (the HE method). We compared the performance of the proposed method with a method using texture features that have been widely used in previous studies. Two classification tests were performed, leave-one-ROI-out cross-validation (CV) and leave-one-specimen-out CV. As a result, the proposed method obtained a classification accuracy of 95.0% for ROI-based CV and 78.3% for specimen-based CV.","PeriodicalId":214897,"journal":{"name":"2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133181870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Scale Adaptive Filters 尺度自适应滤波器

2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA) Pub Date : 2015-11-01 DOI: 10.1109/DICTA.2015.7371304

R. Marchant

引用次数: 1

Textons for 3D Binary Data with Applications to Classifying Cancellous Bone 三维二进制数据的纹理及其在松质骨分类中的应用

2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA) Pub Date : 2015-11-01 DOI: 10.1109/DICTA.2015.7371312

B. Martin, M. Bottema

引用次数: 5