Object Recognition by a Cascade of Edge Probes

Carmichael, Owen; Hebert, Martial

doi:10.5244/c.16.8

Cited by 22 publications

(8 citation statements)

References 32 publications

(23 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the methodology in [21] is not specific to face detection and was effectively applied to other cases [3]. The designer of a cascade does not need an advanced task-specific classifiers, although doing so can improve the overall performance of the system.…”

Section: Introductionmentioning

confidence: 99%

Automatic Design of Cascaded Classifiers

Grossmann

2004

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Cascades of boosted classifiers have become increasingly popular in machine vision and have generated a lot of recent research. Most of it has focused on modifying the underlying Adaboost method and far less attention has been given to the problem of dimensioning the cascade, i.e. determining the number and the characteristics of the boosted classifiers. To a large extent, the designer of a cascade must set the parameters in the cascade using ad-hoc methods. We propose to automatically build a cascade of classifiers, given just a family of weak classifiers a desired performance level and little more. First, a boosted classifier with the desired performance is built using any boosting method. This classifier is then "sliced" using dynamic programming into a cascade of classifiers in a nearly computation-cost-optimal fashion.

show abstract

Section: Introductionmentioning

confidence: 99%

Automatic Design of Cascaded Classifiers

Grossmann

2004

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Conversely, learning-based methods operating on raw pixels or low-level local features have been quite succesful for such applications as face detection [24,18,12,7,25,21], but they have yet to be applied succesfully to shape-based, pose-invariant object recognition. One of the central questions addressed in this paper is how methods based on global templates and methods based on local features compare on invariant shape classification tasks.…”

Section: The Norb Datasetmentioning

confidence: 99%

Learning methods for generic object recognition with invariance to pose and lighting

LeCun

Huang

Bottou

Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004.

934

628

View full text Add to dashboard Cite

We assess the applicability of several popular learning methods for the problem of recognizing generic visual categories with invariance to pose, lighting, and surrounding clutter. A large dataset comprising stereo image pairs of 50 uniform-colored toys under 36 angles, 9 azimuths, and 6 lighting conditions was collected (for a total of 194,400 individual images). The objects were 10 instances of 5 generic categories: four-legged animals, human figures, airplanes, trucks, and cars. Five instances of each category were used for training, and the other five for testing. Low-resolution grayscale images of the objects with various amounts of variability and surrounding clutter were used for training and testing. Nearest Neighbor methods, Support Vector Machines, and Convolutional Networks, operating on raw pixels or on PCA-derived features were tested. Test error rates for unseen object instances placed on uniform backgrounds were around 13% for SVM and 7% for Convolutional Nets. On a segmentation/recognition task with highly cluttered images, SVM proved impractical, while Convolutional nets yielded 14% error. A real-time version of the system was implemented that can detect and classify objects in natural scenes at around 10 frames per second.

show abstract

“…The problem of determining the position of the teacher may seem trivial, and several edge-based algorithms have been suggested for similar tasks [23,24], however, their results are sensitive to camera motion and changes in light intensities. We propose a pixel-ratio comparison-based robust algorithm that accurately segments the teacher.…”

Section: Teacher Segmentationmentioning

confidence: 99%

Content-based adaptive compression of educational videos using phase correlation techniques

et al. 2006

View full text Add to dashboard Cite

A serious bottleneck towards multimedia elearning is the non-availability of required bandwidth to view the lecture videos at good resolution because of large size of lecture videos. Content-based compression of video data can greatly enhance the bandwidth utilization over scarce resource networks. In this paper, an educational video compression technique is presented that dynamically allocates the space according to the content importance of each video segment in the educational videos. We present a phase-correlation-based motion estimation and compensation algorithm that assists in the compression of important moving objects in an efficient manner. Temporal coherence is exploited in a two-phase manner. First, the frames with high similarity are categorized and encoded efficiently. Second, the compression ratio is adapted according to the frame content. Shots that are of high importance are stored at a higher bit rate as compared to the frames of relatively low importance. The importance and priority of the frames is computed automatically by our algorithm. Results over several hours of educational videos and comparison with the state-of-the-art compression algorithms illustrate the high compression performance of our technique.

show abstract

Object Recognition by a Cascade of Edge Probes

Cited by 22 publications

References 32 publications

Automatic Design of Cascaded Classifiers

Automatic Design of Cascaded Classifiers

Learning methods for generic object recognition with invariance to pose and lighting

Content-based adaptive compression of educational videos using phase correlation techniques

Contact Info

Product

Resources

About