In this paper we present a novel image classification framework, which is able to automatically re-configure and adapt its feature-driven classifiers and improve its performance based on user interaction during on-lin...
详细信息
ISBN:
(纸本)9783540795469
In this paper we present a novel image classification framework, which is able to automatically re-configure and adapt its feature-driven classifiers and improve its performance based on user interaction during on-line processing mode. Special emphasis is placed on the generic applicability of the framework to arbitrary surface inspection systems.,the basic components of the framework include: recognition of regions of interest (objects), adaptive feature extraction, dealing with hierarchical information in classification, initial batch training with redundancy deletion and feature selection components, on-line adaptation and refinement of the classifiers based on operators' feedback, and resolving contradictory inputs from several operators by ensembling outputs from different individual classifiers. the paper presents an outline on each of these components and concludes with a thorough discussion of basic and improved off-line and on-line classification results for artificial data sets and real-world images recorded during a CD imprint production process.
One of the most invasive and persistent kind of weed in agriculture is Rumex Obtusifolius L. also called "Broad-leaved Dock". the origin of the plant is Europe and northern Asia, but it has also been reporte...
详细信息
In this work we present a framework of automatic non-photorealistic imageprocessing techniques that create simplified stylistic illustrations from color images, videos and 3D renderings. To smooth low-contrast region...
详细信息
In this paper authors have presented a novel approach for human machine interaction (HMI) that can be used to give alphabets as input to Internet browser in an interactive Set top box withthis added facility. the dev...
详细信息
In this paper authors have presented a novel approach for human machine interaction (HMI) that can be used to give alphabets as input to Internet browser in an interactive Set top box withthis added facility. the device is designed with a MEMS sensor which can be worn on fingertip to send alphabetical input to an interactive set top box. Users write the English alphabet in capital letter by just using the sensor attached to their hand. then this data is undergone some filtering and finally it is sent to the recognition module. the features used for recognition consists of chain code based and un-directional un-weighted graph based features. Each of them recognizes the input character with some confidence factor lying in the closed interval (0,1). Final decision about the recognized character is made by using multifactorial approach. We get a recognition accuracy of more than 90%. We have tested the system withthe inputs given by 22 users (16 male and 6 female) each of the user is asked to write the each letter 5 times.
this paper proposes a transform domain data-hiding scheme for quality access control of images. the original image is decomposed into tiles by applying n-level lifting-based discrete wavelet transformation (DWT). A bi...
详细信息
this paper proposes a transform domain data-hiding scheme for quality access control of images. the original image is decomposed into tiles by applying n-level lifting-based discrete wavelet transformation (DWT). A binary watermark image (external information) is spatially dispersed using the sequence of number generated by a secret key. the encoded watermark bits are then embedded into all DWT-coefficients of n th -level and only in the high-high (HH) coefficients of the subsequent levels using dither modulation (DM) but without complete self-noise suppression. It is well known that due to insertion of external information, there will be degradation in visual quality of the host image (cover). the degree of deterioration depends on the amount of external data insertion as well as step size used for DM. If this insertion process is reverted, better quality of images can be accessed. To achieve that goal, watermark bits are detected using minimum distance decoder and the remaining self-noise due to information embedding is suppressed to provide better quality of image. the simulation results have shown the validity of this claim.
the intelligent sensory system is required to ensure the accurate welding performance. this paper describes the development of an intelligent vision sensor for the robotic laser welding. the sensor system includes a P...
the intelligent sensory system is required to ensure the accurate welding performance. this paper describes the development of an intelligent vision sensor for the robotic laser welding. the sensor system includes a PC based vision camera and a stripe-type laser diode. A set of robust imageprocessing algorithms are implemented. the laser-stripe sensor can measure the profile of the welding object and obtain the seam line. Moreover, the working distance of the sensor can be changed and other configuration is adjusted accordingly. the robot, the seam tracking system, and CW Nd:YAG laser are used for the laser welding robot system. the simple and efficient control scheme of the whole system is also presented. the profile measurement and the seam tracking experiments were carried out to validate the operation of the system.
In this paper we present a new practical camera characterization technique to improve color accuracy in high dynamic range (HDR) imaging. Camera characterization refers to the process of mapping device-dependent signa...
详细信息
In this paper we present a new practical camera characterization technique to improve color accuracy in high dynamic range (HDR) imaging. Camera characterization refers to the process of mapping device-dependent signals, such as digital camera RAW images, into a well-defined color space. this is a well-understood process for low dynamic range (LDR) imaging and is part of most digital cameras - usually mapping from the raw camera signal to the sRGB or Adobe RGB color space. this paper presents an efficient and accurate characterization method for high dynamic range imaging that extends previous methods originally designed for LDR imaging. We demonstrate that our characterization method is very accurate even in unknown illumination conditions, effectively turning a digital camera into a measurement device that measures physically accurate radiance values - both in terms of luminance and color - rivaling more expensive measurement instruments.
In the area of depth estimation from images an interesting approach has been structure recovery from defocus cue. Towards this end, there have been a number of approaches [4,6]. Here we propose a technique to estimate...
详细信息
In the area of depth estimation from images an interesting approach has been structure recovery from defocus cue. Towards this end, there have been a number of approaches [4,6]. Here we propose a technique to estimate the regularized depth from defocus using diffusion. the coefficient of the diffusion equation is modeled using a pair-wise Markov random field (MRF) ensuring spatial regularization to enhance the robustness of the depth estimated. this framework is solved efficiently using a graph-cuts based techniques. the MRF representation is enhanced by incorporating a smoothness prior that is obtained from a graph based segmentation of the input images. the method is demonstrated on a number of data sets and its performance is compared with state of the art techniques.
We present a novel eigenspace-based framework to model a dynamic hand gesture that incorporates both hand shape as well as trajectory information. We address the problem of choosing a gesture set that models an upper ...
详细信息
We present a novel eigenspace-based framework to model a dynamic hand gesture that incorporates both hand shape as well as trajectory information. We address the problem of choosing a gesture set that models an upper bound on gesture recognition efficiency. We show encouraging experimental results on a such a representative set. (c) 2006 Elsevier B.V. All rights reserved.
We propose a face recognition method that fuses information acquired from global and local features of the face for improving performance. Principle components analysis followed by Fisher analysis is used for dimensio...
详细信息
We propose a face recognition method that fuses information acquired from global and local features of the face for improving performance. Principle components analysis followed by Fisher analysis is used for dimensionality reduction and construction of individual feature spaces. Recognition is done by probabilistically fusing the confidence weights derived from each feature space. the performance of the method is validated on FERET and AR databases. (c) 2006 Elsevier B.V. All rights reserved.
暂无评论