Shape Recognition Scheme Research Articles

Real-time shape recognition scheme on projected capacitive touchscreens

Most modern mobile devices are equipped with touchscreens as the main input hardware. Users can write text or draw shapes on the touchscreen to interact with apps. Therefore, accurate recognition of users’ freehand sketches becomes crucial for a device to receive correct instructions from users. This paper proposes a real-time scheme to recognize shapes drawn on the touchscreen. The proposed shape recognition scheme includes preprocessing, feature extraction and shape classification stages. Freehand strokes drawn by users are usually distorted and inaccurate. In preprocessing, this study uses the sampling technique to remove drawing imperfections such as small jagged noise or distorted strokes. In the feature extraction, we use a state machine to extract the length and curvature as the intrinsic features of a shape. In the final shape classification stage, a template-based approach is used to classify the input shape. A fitness score of the input shape to a template is calculated and the template with the highest score is chosen as the most matched shape. Experiment results show that the proposed real-time shape recognition has high accuracy and good performance.

A Real-time Shape Recognition Scheme for Hardware Implementation

We present a shape recognition scheme for real-time embedded systems. It was hard to achieve real-time processing on the typical embedded systems. After analyzing the overall image processing and shape recognition process, we introduced massively parallel processing schemes, and finally implemented special purpose FPGA chips. Strengthen with this FPGA implementation, our target board achieved real-time shape recognition. A two-leg walking robot was directed to the target positions after the shape recognition, for demonstration purpose. We will extend these real-time shape recognition schemes for other image processing applications.

Application of 3D Zernike descriptors to shape-based ligand similarity searching

BackgroundThe identification of promising drug leads from a large database of compounds is an important step in the preliminary stages of drug design. Although shape is known to play a key role in the molecular recognition process, its application to virtual screening poses significant hurdles both in terms of the encoding scheme and speed.ResultsIn this study, we have examined the efficacy of the alignment independent three-dimensional Zernike descriptor (3DZD) for fast shape based similarity searching. Performance of this approach was compared with several other methods including the statistical moments based ultrafast shape recognition scheme (USR) and SIMCOMP, a graph matching algorithm that compares atom environments. Three benchmark datasets are used to thoroughly test the methods in terms of their ability for molecular classification, retrieval rate, and performance under the situation that simulates actual virtual screening tasks over a large pharmaceutical database. The 3DZD performed better than or comparable to the other methods examined, depending on the datasets and evaluation metrics used. Reasons for the success and the failure of the shape based methods for specific cases are investigated. Based on the results for the three datasets, general conclusions are drawn with regard to their efficiency and applicability.ConclusionThe 3DZD has unique ability for fast comparison of three-dimensional shape of compounds. Examples analyzed illustrate the advantages and the room for improvements for the 3DZD.

Detection of dominant points on an object boundary: a discontinuity approach

In a typical partial shape recognition scheme, each scene or model object is decomposed into a concise representation formed by a sequence of contiguous primitive features terminated by pairs of dominant points. A scene object is classified as a model object if its representations are similar. The main problem of this approach is caused by the inconsistency of the dominant point distributions as images of the same object are taken under different levels of noise interference and spatial variations. In this paper a robust dominant point detection algorithm is presented. The technique employs optimal discontinuity detectors for locating the structural nodes of an object boundary with high noise rejection and accurate localization capabilities. Members of a structural node include corners and the terminals of lines and arc segments which are unaffected by spatial variations. The algorithm has been tested with images of a set of hand tools grabbed under different scaling, camera orientations and noise interference. For the majority of cases, a similar set of dominant points is obtained for different images of the same object. The encouraging results demonstrate the feasibility of the approach and its potential as a reliable basis for object recognition.

Binary shape recognition using the morphological skeleton transform

Binary image representation by its morphological skeleton transform has been proposed in the past as an information preserving representation. In this paper this skeleton representation is adopted as the start point for the development of a binary shape recognition scheme. A skeleton matching algorithm is presented that efficiently characterizes the similarity between two skeletons as a distance measure. This skeleton matching algorithm resembles the well known from speech processing elastic matching technique.

A shape recognition scheme based on relative distances of feature points from the centroid

In this paper, a simple but efficient scheme to recognize shapes is proposed. In our scheme, all of the boundary points are used to calculate the centroid of an object, then the distance between each feature point and the centroid is computed. We have shown that the time complexity of our shape matching algorithm is O( m), where m is the number of feature points. The most important advantage of our method is its independence to translation, rotation and scaling of objects.

Fast classification of discrete shape contours

A fast and novel nonoverlapping planar shape recognition scheme with efficiency virtually independent of the number of prototypes is developed. It is composed of new contour normalization, control point extraction and discriminant analysis algorithms also presented here. The system thus applies to shapes regardless of their position, size and orientation. A related shape inspection scheme for detecting locations of shape flaws based on similar principles is also demonstrated.

Automated computer evaluation of time-varying cryomicroscopical images

A system has been developed to perform automatic computerized recognition, tracking, and quantitative morphological analysis of viable cells in freezing solutions. Cryomicroscopical image sequences of freezing cells are digitized and analyzed by computer. Image-processing techniques are used which are insensitive to contrast fluctuations from image to image, and which perform well even in noisy, cluttered images. The generalized Hough transform is used for shape detection, and a heuristic graph-search boundary completion algorithm is applied for shape extraction. The extracted cell shape may be analyzed for changes in cross-sectional area, perimeter length, shape deformation, and other metrics of interest. Knowledge from the shapeextraction phase is used to form a prediction of what shape the cell will be in the next image frame, and thus what to look for in the next shape-detection phase. This combination of knowledge-feedback with a powerful shape-detection technique produces an automatic, dynamic shape-recognition scheme capable of accurate recognition and analysis of the cells regardless of how deformed they may become during the freezing sequence. Example performance of the system is illustrated for a series of micrographs of freezing granulocytes.