Lu Zheng
Email Address
dcsluzhe@nus.edu.sg
9 results
Publication Search Results
Now showing 1 - 9 of 9
Publication A new in-camera imaging model for color computer vision and its application(2012) Kim, S.J.; Lin, H.T.; Lu, Z.; Süsstrunk, S.; Lin, S.; Brown, M.S.; COMPUTER SCIENCEWe present a study of in-camera image processing through an extensive analysis of more than 10,000 images from over 30 cameras. The goal of this work is to investigate if image values can be transformed to physically meaningful values, and if so, when and how this can be done. From our analysis, we found a major limitation of the imaging model employed in conventional radiometric calibration methods and propose a new in-camera imaging model that fits well with today's cameras. With the new model, we present associated calibration procedures that allow us to convert sRGB images back to their original CCD RAW responses in a manner that is significantly more accurate than any existing methods. Additionally, we show how this new imaging model can be used to build an image correction application that converts an sRGB input image captured with the wrong camera settings to an sRGB output image that would have been recorded under the correct settings of a specific camera. © 2012 IEEE.Publication A framework for ultra high resolution 3D imaging(2010) Lu, Z.; Tai, Y.-W.; Ben-Ezra, M.; Brown, M.S.; COMPUTER SCIENCEWe present an imaging framework to acquire 3D surface scans at ultra high-resolutions (exceeding 600 samples per mm2). Our approach couples a standard structured-light setup and photometric stereo using a large-format ultrahigh-resolution camera. While previous approaches have employed similar hybrid imaging systems to fuse positional data with surface normals, what is unique to our approach is the significant asymmetry in the resolution between the low-resolution geometry and the ultra-high-resolution surface normals. To deal with these resolution differences, we propose a multi-resolution surface reconstruction scheme that propagates the low-resolution geometric constraints through the different frequency bands while gradually fusing in the high-resolution photometric stereo data. In addition, to deal with the ultra-high-resolution images, our surface reconstruction is performed in a patch-wise fashion and additional boundary constraints are used to ensure patch coherence. Based on this multi-resolution reconstruction scheme, our imaging framework can produce 3D scans that show exceptionally detailed 3D surfaces far exceeding existing technologies. ©2010 IEEE.Publication Synthesizing oil painting surface geometry from a single photograph(2012) Luo, W.; Lu, Z.; Wang, X.; Xu, Y.-Q.; Ben-Ezra, M.; Tang, X.; Brown, M.S.; COMPUTER SCIENCEWe present an approach to synthesize the subtle 3D relief and texture of oil painting brush strokes from a single photograph. This task is unique from traditional synthesize algorithms due to its mixed modality between the input and output; i.e., our goal is to synthesize surface normals given an intensity image input. To accomplish this task, we propose a framework that first applies intrinsic image decomposition to produce a pair of initial normal maps. These maps are combined into a conditional random field (CRF) optimization framework that incorporates additional information derived from a training set consisting of normals captured using photometric stereo on oil paintings with similar brush styles. Additional constraints are incorporated into the CRF framework to further ensures smoothness and preserve brush stroke edges. Our results show that this approach can produce compelling reliefs that are often indistinguishable from results captured using photometric stereo. © 2012 IEEE.Publication VideoAder: A video advertising system based on intelligent analysis of visual content(2011) Hu, J.; Li, G.; Lu, Z.; Xiao, J.; Hong, R.; COMPUTER SCIENCERecent years have witnessed the prevalence of context based video advertisement. However, those advertisement systems solely take the metadata into account, such as titles, descriptions and tags. In this paper, we present a novel video advertising system called VideoAder. The system leverages the rich information from the video corpus for embedding visual content relevant ads. Given a product, we utilize content-based object retrieval technique to identify the relevant ads and their potential embedding positions in the video stream. Specifically, the "Single-Merge" and "Merge" methods are proposed to tackle the complex query. Typical Feature Intensity (TFI) is used to train a classifier to automatically deciding which method is better in one situation. Experimental results demonstrated the feasibility of the system. © 2011 ACM.Publication A 3D imaging framework based on high-resolution photometric-stereo and low-resolution depth(2013) Lu, Z.; Tai, Y.-W.; Deng, F.; Ben-Ezra, M.; Brown, M.S.; COMPUTER SCIENCEThis paper introduces a 3D imaging framework that combines high-resolution photometric stereo and low-resolution depth. Our approach targets imaging scenarios based on either macro-lens photography combined with focal stacking or a large-format camera that are able to image objects with more than 600 samples per mm2. These imaging techniques allow photometric stereo algorithms to obtain surface normals at resolutions that far surpass corresponding depth values obtained with traditional approaches such as structured-light, passive stereo, or depth-from-focus. Our work offers two contributions for 3D imaging based on these scenarios. The first is a multi-resolution, patched-based surface reconstruction scheme that can robustly handle the significant resolution difference between our surface normals and depth samples. The second is a method to improve the initial normal estimation by using all the available focal information for images obtained using a focal stacking technique. © 2012 Springer Science+Business Media New York.Publication Interactive degraded document binarization: An example (and case) for interactive computer vision(2009) Lu, Z.; Wu, Z.; Brown, M.S.; COMPUTER SCIENCEThis paper describes a user-assisted application to perform adaptive thresholding (i.e. binarization) on degraded handwritten documents. While existing adaptive thresholding techniques purport to be automatic, they in fact require the user to perform non-intuitive parameter tuning to obtain satisfactory results. In our work, we recast the problem into one where the user needs only to coarsely markup regions in the thresholded image that have unsatisfactory results. These regions are then segmented and processed locally - no parameter tuning is necessary. Our user study shows that not only do the majority of users prefer our application over parameter tuning, but our final results are better than existing algorithms due to the more targeted processing. While our main contribution is an effective user-assisted application for document binarization, we use this as an example to advocate the need to rethink how many computer vision solutions, notoriously reliant on parameter tuning, can be reworked to exploit meaningful user interaction. © 2009 IEEE.Publication Directed assistance for ink-bleed reduction in old documents(2009) Lu, Z.; Wu, Z.; Brown, M.S.; COMPUTER SCIENCEInk-bleed interference is a serious problem that affects the legibility of old documents. Ink-bleed can be reduced using pixel classification based on user-supplied markup that labels examples of ink-bleed, foreground-ink, and background. The main challenge is ensuring that the user's markup sufficiently captures the characteristics of the document. This is particularly troublesome for old documents that can exhibit significant change within the same page. In this paper, we address this markup problem using a "directed assistance" approach in which the user provides a small amount of initial markup. The image is then classified and regions with low classification confidence are grouped and displayed to the user for another round of markup. The key idea is to direct the user to where markup is needed. In addition, local markup can be weighted in the classification algorithm to produce better results. © 2009 IEEE.Publication Wiimote viewer enhances resident case conferences(2010) Amans, M.R.; Shih, G.; Zheng, L.; Yeh, C.; Brown, M.; COMPUTER SCIENCEPublication BinarizationShop: A user-assisted software suite for converting old documents to black-and-white(2010) Deng, F.; Wu, Z.; Lu, Z.; Brown, M.S.; COMPUTER SCIENCEConverting a scanned document to a binary format (black and white) is a key step in the digitization process. While many existing binarization algorithms operate robustly for well-kept documents, these algorithms often produce less than satisfactory results when applied to old documents, especially those degraded with stains and other discolorations. For these challenging documents, user assistance can be advantageous in directing the binarization procedure. Many existing algorithms, however, are poorly designed to incorporate user assistance. In this paper, we discuss a software framework, BinarizationShop, that combines a series of bi-narization approaches that have been tailored to exploit user assistance. This framework provides a practical approach for converting difficult documents to black and white. © 2010 ACM.