Probabilistic modeling of local appearance and spatial relationships for object recognition

Schneiderman, Henry; Kanade, Takeo

doi:10.1109/cvpr.1998.698586

Cited by 246 publications

(148 citation statements)

References 15 publications

Supporting

Mentioning

148

Contrasting

Order By: Relevance

“…In these experiments, we noticed some differences in performance between the detector described in this paper and an improved version of the detector we described in Schneiderman and Kanade (1998). Both detectors use similar probabilistic structures, but the (b) Figure 13.…”

Section: Results In Face Detectionmentioning

confidence: 91%

“…The wavelet-based detector described in this paper performs much better for profileview faces. However, the localized eigenimage-based detector in Schneiderman and Kanade (1998) seems to be slightly more accurate on frontal faces.…”

Section: Results In Face Detectionmentioning

confidence: 99%

“…(Continued. ) detector in Schneiderman and Kanade (1998) uses local operators based on localized eigenimages rather than wavelet coefficients. The wavelet-based detector described in this paper performs much better for profileview faces.…”

Section: Results In Face Detectionmentioning

confidence: 99%

See 2 more Smart Citations

Object Detection Using the Statistics of Parts

Schneiderman

Kanade

2004

International Journal of Computer Vision

283

154

View full text Add to dashboard Cite

Abstract. In this paper we describe a trainable object detector and its instantiations for detecting faces and cars at any size, location, and pose. To cope with variation in object orientation, the detector uses multiple classifiers, each spanning a different range of orientation. Each of these classifiers determines whether the object is present at a specified size within a fixed-size image window. To find the object at any location and size, these classifiers scan the image exhaustively.Each classifier is based on the statistics of localized parts. Each part is a transform from a subset of wavelet coefficients to a discrete set of values. Such parts are designed to capture various combinations of locality in space, frequency, and orientation. In building each classifier, we gathered the class-conditional statistics of these part values from representative samples of object and non-object images. We trained each classifier to minimize classification error on the training set by using Adaboost with Confidence-Weighted Predictions . In detection, each classifier computes the part values within the image window and looks up their associated classconditional probabilities. The classifier then makes a decision by applying a likelihood ratio test. For efficiency, the classifier evaluates this likelihood ratio in stages. At each stage, the classifier compares the partial likelihood ratio to a threshold and makes a decision about whether to cease evaluation-labeling the input as non-object-or to continue further evaluation. The detector orders these stages of evaluation from a low-resolution to a high-resolution search of the image. Our trainable object detector achieves reliable and efficient detection of human faces and passenger cars with out-of-plane rotation.

show abstract

Section: Results In Face Detectionmentioning

confidence: 91%

Section: Results In Face Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Object Detection Using the Statistics of Parts

Schneiderman

Kanade

2004

International Journal of Computer Vision

283

154

View full text Add to dashboard Cite

show abstract

“…<Table 1> shows a simple comparison between our method and other existing methods. The probabilistic method based on local measurements requires small portions of objects to recognize the whole objects, but it required extensive training processes to recognize occluded objects [3,16,15].…”

Section: Resultsmentioning

confidence: 99%

Partial Object Recognition based on Ellipse of Objects using Symmetry in Image Databases

Cho¹

2008

The KIPS Transactions:PartB

View full text Add to dashboard Cite

This paper discusses the problem of partial object recognition in image databases. We propose the method to reconstruct and estimate partially occluded shapes and regions of objects in images from overlapping and cutting. We present the robust method for recognizing partially occluded objects based on symmetry properties, which is based on an ellipse of objects. Our method provides simple techniques to reconstruct occluded regions via a region copy using the symmetry axis within an object. Since our method relies on reconstruction of the object based on the symmetry rather than statistical estimates, it has proven to be remarkably robust in recognizing partially occluded objects in the presence of scale changes, rotation, and viewpoint changes.

show abstract

“…All the above mentioned methods share a common characteristic, that is, they are mainly focused on frontal face detection. A limited number of attempts to build profile or non-frontal face detectors are reported [29], [30], [31], [32].…”

Section: Face Detection Based On Fusion Of Informationmentioning

confidence: 99%

A monocular system for person tracking: Implementation and testing

Stamou

Krinidis

Nikolaidis

et al. 2007

J Multimodal User Interfaces

View full text Add to dashboard Cite

This paper presents a complete functional system capable of detecting people and tracking their motion in either live camera feed or pre-recorded video sequences. The system consists of two main modules, namely the detection and tracking modules. Automatic detection aims at locating human faces and is based on fusion of color and feature-based information. Thus, it is capable of handling faces in different orientations and poses (frontal, profile, intermediate). To avoid false detections, a number of decision criteria are employed. Tracking is performed using a variant of the well-known Kanade-Lucas-Tomasi tracker, while occlusion is handled through a re-detection stage. Manual intervention is allowed to assist both modules if required. In manual mode, the system can track any object of interest, so long as there are enough features to track. The system caters for calibrated cameras and can provide 3-D coordinates of any tracked object(s) of interest. It has been tested with very good results on a variety of video sequences, including a database of studio video sequences, for which 3-D ground truth data, originating from a 4-camera infrared tracking system, exist.

show abstract

Probabilistic modeling of local appearance and spatial relationships for object recognition

Abstract: In this paper, we describe an algorithm for object recognition

Cited by 246 publications

References 15 publications

Object Detection Using the Statistics of Parts

Object Detection Using the Statistics of Parts

Partial Object Recognition based on Ellipse of Objects using Symmetry in Image Databases

A monocular system for person tracking: Implementation and testing

Contact Info

Product

Resources

About