Standard test image

About: Standard test image is a research topic. Over the lifetime, 5217 publications have been published within this topic receiving 98486 citations.

Adaptive Nonparametric Image Parsing

Abstract: In this paper, we present an adaptive nonparametric solution to the image parsing task, namely, annotating each image pixel with its corresponding category label. For a given test image, first, a locality-aware retrieval set is extracted from the training data based on superpixel matching similarities, which are augmented with feature extraction for better differentiation of local superpixels. Then, the category of each superpixel is initialized by the majority vote of the $k$ -nearest-neighbor superpixels in the retrieval set. Instead of fixing $k$ as in traditional nonparametric approaches, here, we propose a novel adaptive nonparametric approach that determines the sample-specific $k$ for each test image. In particular, $k$ is adaptively set to be the number of the fewest nearest superpixels that the images in the retrieval set can use to get the best category prediction. Finally, the initial superpixel labels are further refined by contextual smoothing. Extensive experiments on challenging data sets demonstrate the superiority of the new solution over other state-of-the-art nonparametric solutions.

Digital Image Processing Systems

Abstract: Universal digital image processing systems in europe - A comparative survey.- Cello an interactive system for image analysis.- A knowledge-based interactive robot-vision system.- Real-time processing of binary images for industrial applications.- CPO-2/K-202: A universal digital image analysis system.- The gop parallel image processor.- Object detection in infrared images.

Physiological face recognition is coming of age

Abstract: The previous work of the authors has shown that physiological information on the face can be extracted from thermal infrared imagery and can be used as a biometric. Although, that work has proved the feasibility of physiological face recognition, the experimental results revealed high false acceptance rates due to methodological weaknesses in the feature extraction and matching algorithms. This paper, presents a new methodology that corrects these problems and yields high recognition rates. Specifically, a post-processing algorithm removes fake vascular contours, which degraded performance. Also, a new vascular network matching algorithm copes with deformations caused by varying facial pose and expressions. First, it estimates the facial pose in the test image and then calculates the deformation of the vascular network in the database image. Next, it registers test and database vascular networks using the dual bootstrap iterative closest point (ICP) matching algorithm. Finally, it computes a matching score between the vascular networks, which is a function of overlapping vessel pixels. Extensive experiments have been undertaken to test the new method. The results highlight its superiority.

Image guided acquisition of quantitative dual energy data

Abstract: A technique for establishing texture metrics and bone mineral density (BMD) within an anatomical region of interest. A digital imaging system is used to acquire a standard digital X-ray image with a wide field of view. The standard digital X-ray image is used to guide the imaging system to obtain an image of a region of interest. The standard digital X-ray image is used to calculate various texture metrics, such as a length of a fracture. A dual-energy digital X-ray image of the region of interest is acquired. The dual-energy digital X-ray image is corrected for scatter. The BMD of the region of interest may be established from the scatter-corrected dual-energy digital X-ray image. The BMD, the texture metrics, and/or the scatter-corrected dual-energy X-ray image may be displayed on the standard digital X-ray image.

Event-related potential component associated with the recognition of three-dimensional objects.

Abstract: To understand the physiological process underlying view-invariant object recognition, we designed a delayed matching-to-sample task under two different conditions: in the first condition, the sample and test stimuli were presented in the same view, and in the second, the two stimuli were presented in different views. The event-related potential (ERP) component, posterior N1, exhibited a significantly larger amplitude when the test image was in the same view as the sample image than when the test and the sample images were in different views. The result indicates that the posterior N1 is significantly sensitive to view association, and clarifies the difference between the neuronal activity that occurs in 3D object recognition and 2D image identification at the level of N1.