IEEE Transactions on Image Processing
Learning to Recognize Objects in Images Using Anisotropic Nonparametric Kernels
Proceedings of the 2010 conference on Biologically Inspired Cognitive Architectures 2010: Proceedings of the First Annual Meeting of the BICA Society
Fast and efficient saliency detection using sparse sampling and kernel density estimation
SCIA'11 Proceedings of the 17th Scandinavian conference on Image analysis
A novel feature extraction method for face recognition under different lighting conditions
CCBR'11 Proceedings of the 6th Chinese conference on Biometric recognition
A saliency detection model based on local and global kernel density estimation
ICONIP'11 Proceedings of the 18th international conference on Neural Information Processing - Volume Part I
Public Space Behavior Modeling With Video and Sensor Analytics
Bell Labs Technical Journal
Force work induced metric for face verification
IScIDE'12 Proceedings of the third Sino-foreign-interchange conference on Intelligent Science and Intelligent Data Engineering
Hi-index | 0.14 |
We present a generic detection/localization algorithm capable of searching for a visual object of interest without training. The proposed method operates using a single example of an object of interest to find similar matches, does not require prior knowledge (learning) about objects being sought, and does not require any preprocessing step or segmentation of a target image. Our method is based on the computation of local regression kernels as descriptors from a query, which measure the likeness of a pixel to its surroundings. Salient features are extracted from said descriptors and compared against analogous features from the target image. This comparison is done using a matrix generalization of the cosine similarity measure. We illustrate optimality properties of the algorithm using a naive-Bayes framework. The algorithm yields a scalar resemblance map, indicating the likelihood of similarity between the query and all patches in the target image. By employing nonparametric significance tests and nonmaxima suppression, we detect the presence and location of objects similar to the given query. The approach is extended to account for large variations in scale and rotation. High performance is demonstrated on several challenging data sets, indicating successful detection of objects in diverse contexts and under different imaging conditions.