Image Processing, Machine Vision, Pattern Recognition, Video and Display http://scitation.aip.org/ Image Processing, Machine Vision, Pattern Recognition, Video and Display Modified correlation criterion for digital image correlation considering the effect of lighting variations in deformation measurements http://link.aip.org/link/?JOE/51/017004/1&agg=rss Bei Peng, Qiushu Zhang, Wu Zhou, Xiaohong Hao, and Li Ding<br/> The Newton-Raphson (N-R) algorithm based on the sum of squared differences (SSD) function used in the digital image correlation (DIC) may obtain unreliable results in deformation measurements because light source variation is not taken into account. Here, a modified N-R algorithm that includes the e ... [Opt. Eng. 51, 017004 (2012)] published Fri Feb 10, 2012. Real-time multiple plane area detection using a self-organizing map http://link.aip.org/link/?JOE/51/017207/1&agg=rss Jeong-Hyun Kim, Zhu Teng, and Dong-Joong Kang<br/> Plane detection in 3-D space is a core function of the autonomous mobile robot. A representative technique for plane detection is the Hough transform method. The Hough transform is robust to noise and makes accurate plane detection possible. However, a common problem in methods based on the Hough tr ... [Opt. Eng. 51, 017207 (2012)] published Thu Feb 9, 2012. Interactive optimization of photo composition with Gaussian mixture model on mobile platform http://link.aip.org/link/?JOE/51/017001/1&agg=rss Hachon Sung, Guntae Bae, Sunyoung Cho, and Hyeran Byun<br/> A good photo is determined using various visual elements of photography and these elements have been implemented in mobile devices with functionalities including zooming, auto-focusing and auto-white-balancing. Although composition is an important element of a good photo and an interesting research ... [Opt. Eng. 51, 017001 (2012)] published Wed Feb 8, 2012. Reeb graph computation through spectral clustering http://link.aip.org/link/?JOE/51/017209/1&agg=rss Teng Ma, Zhuangzhi Wu, Pei Luo, and Lu Feng<br/> The Reeb graph provides a structure that encodes the topology of a shape, and it has been gaining in popularity in shape analysis and understanding. We introduce a spectral clustering method to compute the Reeb graph. Given a 3-D model embedded in the Euclidean space, we define the Morse function ac ... [Opt. Eng. 51, 017209 (2012)] published Wed Feb 8, 2012. Scene classification based on spatial pyramid representation by superpixel lattices and contextual visual features http://link.aip.org/link/?JOE/51/017201/1&agg=rss Guanghua Gu, Fengcai Li, Yao Zhao, and Zhenfeng Zhu<br/> Natural scene classification is a challenging open problem in computer vision. We present a novel spatial pyramid representation scheme for recognizing scene category. Initially, each image is partitioned into sub-blocks, applying the technology of superpixel lattices segmentation according to a boo ... [Opt. Eng. 51, 017201 (2012)] published Tue Feb 7, 2012. Feature space-based human face image representation and recognition http://link.aip.org/link/?JOE/51/017205/1&agg=rss Yong Xu, Zizhu Fan, and Qi Zhu<br/> We propose a novel face recognition method that represents and classifies face images in the feature space. It first assumes that in the feature space the test sample can be well expressed by a linear combination of the training samples, and then it exploits the obtained linear combination to perfor ... [Opt. Eng. 51, 017205 (2012)] published Tue Feb 7, 2012. Visual fatigue modeling and analysis for stereoscopic video http://link.aip.org/link/?JOE/51/017206/1&agg=rss Jaeseob Choi, Donghyun Kim, Sunghwan Choi, and Kwanghoon Sohn<br/> In this paper, we propose a visual fatigue prediction method for stereoscopic video. We select visual fatigue factor candidates and determine the equations for each. The candidates are then classified into their principal components, and the validity of each is confirmed using principal component an ... [Opt. Eng. 51, 017206 (2012)] published Mon Feb 6, 2012. Wildfire smoke detection using temporospatial features and random forest classifiers http://link.aip.org/link/?JOE/51/017208/1&agg=rss ByoungChul Ko, Joon-Young Kwak, and Jae-Yeal Nam<br/> We propose a wildfire smoke detection algorithm that uses temporospatial visual features and an ensemble of decision trees and random forest classifiers. In general, wildfire smoke detection is particularly important for early warning systems because smoke is usually generated before flames; in addi ... [Opt. Eng. 51, 017208 (2012)] published Mon Feb 6, 2012. Sampling and clustering algorithm for determining the number of clusters based on the rosette pattern http://link.aip.org/link/?JOE/51/017204/1&agg=rss Ali Sadr and Amirkeyvan Momtaz<br/> Clustering is one of the image-processing methods used in non-destructive testing (NDT). As one of the initializing parameters, most clustering algorithms, like fuzzy C means (FCM), Iterative self-organization data analysis (ISODATA), K-means, and their derivatives, require the number of clusters. T ... [Opt. Eng. 51, 017204 (2012)] published Mon Feb 6, 2012. Boundary extraction using supervised edgelet classification http://link.aip.org/link/?JOE/51/017002/1&agg=rss Ji Zhao, Jiayi Ma, Jinwen Tian, Jie Ma, and Sheng Zheng<br/> Traditional learning-based boundary extraction algorithms classify each pixel edge separately and then get boundaries from the local decisions of a classifier. However, we propose a supervised learning method for boundary extraction by using edgelets as boundary elements. First, we extract edgelets ... [Opt. Eng. 51, 017002 (2012)] published Mon Feb 6, 2012. Efficient adaptive deinterlacing algorithm with awareness of closeness and similarity http://link.aip.org/link/?JOE/51/017003/1&agg=rss Jin Wang, Gwanggil Jeon, and Jechang Jeong<br/> We introduces an efficient intra-field deinterlacing algorithm while considering both closeness and similarity between the interpolated pixel and the neighbor pixels. Instead of estimating the edge orientations via limited candidate directions as previous intra-field deinterlacing methods, we propos ... [Opt. Eng. 51, 017003 (2012)] published Mon Feb 6, 2012. Recognition of human activities using a multiclass relevance vector machine http://link.aip.org/link/?JOE/51/017202/1&agg=rss Weihua He, Kin Choong Yow, and Yongcai Guo<br/> We address the issue of human activity recognition by introducing the multiclass relevance vector machine (mRVM), the current state-of-the-art kernel machine learning technology given the multiclass classification problems (actually, activity recognition can commonly be viewed as a multiclass classi ... [Opt. Eng. 51, 017202 (2012)] published Mon Feb 6, 2012. Robust and fast Hausdorff distance for image matching http://link.aip.org/link/?JOE/51/017203/1&agg=rss Hu Zhu, Tianxu Zhang, Luxin Yan, and Lizhen Deng<br/> A robust and fast Hausdorff distance (HD) method is presented for image matching. Canny edge operator is used for extracting edge points. HD measure is one of efficient measures for comparing two edge images by calculating the interpixel distance between two sets of edge points, and does not require ... [Opt. Eng. 51, 017203 (2012)] published Tue Jan 31, 2012. People detection method using graphics processing units for a mobile robot with an omnidirectional camera http://link.aip.org/link/?JOE/50/127204/1&agg=rss Sungil Kang, Annah Roh, Bodam Nam, and Hyunki Hong<br/> This paper presents a novel vision system for people detection using an omnidirectional camera mounted on a mobile robot. In order to determine regions of interest (ROI), we compute a dense optical flow map using graphics processing units, which enable us to examine compliance with the ego-motion of ... [Opt. Eng. 50, 127204 (2011)] published Wed Dec 14, 2011. Gradient domain statistical image-importance model for content-aware image resizing http://link.aip.org/link/?JOE/50/127006/1&agg=rss Chanho Jung, Wonjun Kim, and Changick Kim<br/> We propose a novel image-importance model for content-aware image resizing. In contrast to the previous gradient magnitude-based approaches, we focus on the excellence of gradient domain statistics. The proposed scheme originates from a well-known property of the human visual system that the human v ... [Opt. Eng. 50, 127006 (2011)] published Fri Dec 9, 2011. Novel dynamic Bayesian networks for facial action element recognition and understanding http://link.aip.org/link/?JOE/50/127209/1&agg=rss Wei Zhao, Jeong-Seon Park, Dong-You Choi, and Sang-Woong Lee<br/> In daily life, language is an important tool of communication between people. Besides language, facial action can also provide a great amount of information. Therefore, facial action recognition has become a popular research topic in the field of human-computer interaction (HCI). However, facial act ... [Opt. Eng. 50, 127209 (2011)] published Thu Dec 8, 2011. Lensless ghost imaging for moving objects http://link.aip.org/link/?JOE/50/127005/1&agg=rss Hu Li, Jin Xiong, and Guihua Zeng<br/> Lensless thermal-light ghost imaging of moving objects is investigated. The second-order correlation function of thermal-light ghost imaging of moving objects is obtained by quasistatic approximation. The relationship between the visibility of the ghost imaging and the transverse coherent length l i ... [Opt. Eng. 50, 127005 (2011)] published Wed Dec 7, 2011. Adaptive background modeling in multicamera system for real-time object detection http://link.aip.org/link/?JOE/50/127206/1&agg=rss Massimo Camplani and Luis Salgado<br/> We present an adaptive and efficient background modeling strategy for real-time object detection in multicamera systems. The proposed approach is an innovative multiparameter adaptation strategy of the mixture of Gaussian (MoG) background modeling algorithm. This approach is able to efficiently adju ... [Opt. Eng. 50, 127206 (2011)] published Wed Dec 7, 2011. Three-phase quadrature spectral matching imager using correlation image sensor and wavelength-swept monochromatic illumination http://link.aip.org/link/?JOE/50/127208/1&agg=rss Akira Kimachi, Shigeru Ando, Motonori Doi, and Shogo Nishi<br/> We propose a three-phase spectral matching imager (3PSMI) to realize a novel spectral matching method called quadrature spectral matching (QSM) in real time. The 3PSMI is comprised of the correlation image sensor (CIS) and wavelength-swept monochromatic illumination (WSMI) to perform QSM at each pix ... [Opt. Eng. 50, 127208 (2011)] published Mon Dec 5, 2011. Vision-based method for detecting driver drowsiness and distraction in driver monitoring system http://link.aip.org/link/?JOE/50/127202/1&agg=rss Jaeik Jo, Sung Joo Lee, Ho Gi Jung, Kang Ryoung Park, and Jaihie Kim<br/> Most driver-monitoring systems have attempted to detect either driver drowsiness or distraction, although both factors should be considered for accident prevention. Therefore, we propose a new driver-monitoring method considering both factors. We make the following contributions. First, if the drive ... [Opt. Eng. 50, 127202 (2011)] published Fri Dec 2, 2011. Hand posture recognition via joint feature sparse representation http://link.aip.org/link/?JOE/50/127210/1&agg=rss Chuqing Cao, Ying Sun, Ruifeng Li, and Lin Chen<br/> In this study, we cast hand posture recognition as a sparse representation problem, and propose a novel approach called joint feature sparse representation classifier for efficient and accurate sparse representation based on multiple features. By integrating different features for sparse representat ... [Opt. Eng. 50, 127210 (2011)] published Thu Dec 1, 2011.