Subhajit Sanyal

LogoSeeker: a system for detecting and matching logos in natural images

The dominant advertising model on the Internet is based on matching search keywords or web page content to ads. The matching is based on text content. There is an explosion of media content on the Internet. Matching based on image content has not taken off on the Internet despite the huge popularity of sites like flickr.com. In this demo, we show we can adapt techniques from image matching to enable a logo-based advertisement matching system for photo sharing sites like Flickr. Logo detection is based on detection and matching of salient points.

I-FAC: Efficient Fuzzy Associative Classifier for Object Classes in Images

We present I-FAC, a novel fuzzy associative classification algorithm for object class detection in images using interest points. In object class detection, the negative class CN is generally vague (CN = U − CP ; where U and CP are the universal and positive classes respectively). But, image classification necessarily requires both positive and negative classes for training. I-FAC is a single class image classifier that relies only on the positive class for training. Because of its fuzzy nature, I-FAC also handles polysemy and synonymy (common problems in most crisp (non-fuzzy) image classifiers) very well. As associative classification leverages frequent patterns mined from a given dataset, its performance as adjudged from its false-positive-rate(FPR)-versus-recall curve is very good, especially at lower FPRs when its recall is even better. IFAC has the added advantage that the rules used for classification have clear semantics, and can be comprehended easily, unlike other classifiers, such as SVM, which act as black-boxes. From an empirical perspective (on standard public datasets), the performance of I-FAC is much better, especially at lower FPRs, than that of either bag-of-words (BOW) or SVM (both using interest points).

Detection of pornographic content in internet images

Pornographic image detection is an important and challenging problem. Detection of pornography on the Internet is even more challenging because of the scale (billions of images) and diversity (small to very large images, graphic, grey scale images, etc.) of image content. The performance requirements (precision, recall, and speed) are also very stringent. Because of this, no single technique provides the required performance. In this paper, we describe a framework for detecting images with pornographic content. The framework combines various techniques based on object-level and pixel-level analysis of image content. To enable high-precision, we detect body parts (including faces) in images. For high-recall, low-level techniques like color and texture features are used. For adaptation to new datasets, we also support learning of appropriate color models from weakly-labeled datasets. In addition to image-based analysis, both text-based and site-level analysis are performed. Unlike many adult detection techniques, we explicitly leverage techniques like texture analysis and face detection for non-adult content identification. The multiple cues are combined in a systematic manner using ROC analysis and boosting. Evaluations on real world web data indicate that the system has the best performance among the systems compared.

Fast object detection using local feature-based SVMs

Viola-Jones approach to object detection is by far the most widely used object detection technique because of speed of detection in images with clutter. SVM-based object detection techniques have the disadvantage of slow detection speeds because of exhaustive window search. Appearance-based detection techniques do not generalize well in the presence of pose variations. In this paper, we propose a feature-based technique which classifies salient-points as belonging to object or background classes and performs object detection based on classified key points. Since keypoints are sparse, the technique is very fast. The use of SIFT descriptor provides invariance to scale and pose changes.

A classification based framework for concept summarization

In this paper we propose a novel classification based framework for finding a small number of images that summarize a given concept. Our method exploits metadata information available with the images to get category information using Latent Dirichlet Allocation. Using this category information for each image, we solve the underlying classification problem by building a sparse classifier model for each concept. We demonstrate that the images that specify the sparse model form a good summary. In particular, our summary satisfies important properties such as likelihood, diversity and balance in both visual and semantic sense. Furthermore, the framework allows users to specify desired distributions over categories to create personalized summaries. Experimental results on seven broad query types show that the proposed method performs better than state-of-the-art methods.

A Classification Based Framework for Concept Summarization

In this paper we propose a novel classification based framework for finding a small number of images that summarize a given concept. Our method exploits metadata information available with the images to get category information using Latent Dirichlet Allocation. Using this category information for each image, we solve the underlying classification problem by building a sparse classifier model for each concept. We demonstrate that the images that specify the sparse model form a good summary. In particular, our summary satisfies important properties such as likelihood, diversity and balance in both visual and semantic sense. Furthermore, the framework allows users to specify desired distributions over categories to create personalized summaries.\eat{ We demonstrate the efficacy of our method on seven broad query types - sports, news, celebrities, events, travel, country and abstract.} Experimental results on seven broad query types show that the proposed method performs better than state-of-the-art methods.\eat{ in terms of satisfying important visual and semantic properties both qualitatively and quantitatively. We observe from editorial evaluation that around

3dB: a system for geometric tagging

78

Multi-objective ranking of comments on web

\% of our summaries are of high enough quality to be shown directly to the web users with minimal or no modifications.

METHOD AND SYSTEM FOR CONCEPT SUMARIZATION

There is an explosion of multimedia content, especially image, on the Internet. Images as pixel arrays suffer from two deficiencies: semantic gap and geometric gap. There have been several attempts like object detection for closing the semantic gap. Recently the notion of community tagging of objects in an image has attracted a lot of attention. There has been lot of research in closing the geometric gap by 3D reconstruction. In this paper, we present 3D Buddy (3dB) -a system for geometrically tagging images for 3D reconstruction.