Inference and retrieval of facial images

Attempts have been made to extend SQL to work with multimedia databases. We are reserved on the representation ability of extended SQL to cope with the richness in content of multimedia data. In this paper we present an example of a multimedia database system, Computer Aided Facial Image Inference and Retrieval system (CAFIIR). The system stores and manages facial images and criminal records, providing necessary functions for crime identification. We would like to demonstrate some core techniques for multimedia database with CAFIIR system. Firstly, CAFIIR is a integrated system. Besides database management, there are image analysis, image composition, image aging, and report generation subsystems, providing means for problem solving. Secondly, the richness of multimedia data urges feature-based database for their management. CAFIIR is feature-based. A indexing mechanism,iconic index, has been proposed for indexing facial images using hierarchical self-organization neural network. The indexing method operates on complex feature measures and provides means for visual navigation. Thirdly, special retrieval methods for facial images have been developed, including visual browsing, similarity retrieval, free text retrieval and fuzzy retrieval.     

Investigation of texture effect on visual colour difference evaluation

The texture effect on visual colour difference evaluation was investigated in this study. Five colour centers were selected and textured colour pairs were generated using scanned textile woven fabrics and colour‐mapping technique. The textured and solid colour pairs were then displayed on a characterized cathode ray tube (CRT) monitor for colour difference evaluation. The colour difference values for the pairs with texture patterns are equal to 5.0 CIELAB units in lightness direction. The texture level was represented by the half‐width of histogram, which is called texture strength in this study. High correlation was found between texture strength and visual colour difference for textured colour pairs, which indicates that an increasing of 10 units of texture strength in luminance would cause a decreasing of 0.25 units visual difference for the five colour centers. The ratio of visual difference between textured and solid colour pairs also indicates a high parametric effect of texture. © 2005 Wiley Periodicals, Inc. Col Res Appl, 30, 341–347, 2005; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/col.     

Gigahertz signal processing using reflex optoelectronic switching matrices

The application of reflex optoelectronic switching matrices (ROSM) to signal processing in the gigahertz region is analyzed. Various signal processing functions such as delay generation, loop filtering, word generation/detection, integration, and digital to analog conversion are identified and their respective realizations in a ROSM are presented. It is found that for dedicated signal processing functions, simpler submatrices instead of full matrices can be employed with significant reduction in complexity and cost. The performance of ROSM's using currently commercially available components confirms the feasibility of gigahertz signal processing with ROSM's.     

Embracing transformational leadership: Team values and the impact of leader behavior on team performance.

The authors investigated the relationship between transformational leadership behavior and group performance in 218 financial services teams that were branches of a bank in Hong Kong and the United States. Transformational leadership influenced team performance through the mediating effect of team potency. The effect of transformational leadership on team potency was moderated by team power distance and team collectivism, such that higher power distance teams and more collectivistic teams exhibited stronger positive effects of transformational leadership on team potency. The model was supported by data in both Hong Kong and the United States, which suggests a convergence in how teams function in the East and West and highlights the importance of team values. (PsycINFO Database Record (c) 2011 APA, all rights reserved)     

Training ratio and comparison of trained vector quantizers

The vector quantizer (VQ) codebook is usually designed by clustering a training sequence (TS) drawn from the underlying distribution function. In order to cluster a TS, we may use the K-means algorithm (generalized Lloyd (1982) algorithm) or the self-organizing map algorithm. In this paper, a survey of trained VQ performance is conducted to study the effect of the training ratio on training quantizers. The training ratio, which is defined by the ratio of the TS size to the codebook size, is dependent on the VQ structure. Hence, different VQs may show different training properties, even though the VQs are designed for the same TS. A numerical comparison of trained VQs is then conducted in conjunction with deriving their training ratios. Through the comparison, it is shown that structured VQs can achieve better performance than the full-search scheme if the codebooks are trained by a finite TS. Further, we can derive a design or comparison guideline that maintains equal training ratios in training different VQs.     

Object boundary location by region and contour deformation

Many applications in image analysis need to distinguish an object from its surroundings. The `snake' method (Kass, 1987) is a well known method to solve such problems by locating the object boundary from an initial plan, but it has the limitation that the distance between the initial plan and the object boundary should be `very small'. The authors present a two-step method, which combines region and contour deformation, to locate the boundary of an object from a designated initial boundary plan. First, they propose a new deformable region model to represent an object, and use the model to locate the boundary of the object by region deformation. This step fills the gap between a fairly rough initial plan and the `snake' method. The resulting boundary is then used as the initial plan of a `snake' method to further refine the boundary. The results of the method are shown in simulated images and MRI images of brain tumour patients     

Image compression in digital mammography: effects on computerized detection of subtle microcalcifications

Our previous receiver operating characteristic (ROC) study indicated that the detection accuracy of microcalcifications by radiologists is significantly reduced if mammograms are digitized at 0.1 mm x 0.1 mm. Our recent study also showed that detection accuracy by computer decreases as the pixel size increases from 0.035 mm x 0.035 mm. It is evident that very large matrix sizes have to be used for digitizing mammograms in order to preserve the information in the image. Efficient compression techniques will be needed to facilitate communication and archiving of digital mammograms. In this study, we evaluated two compression techniques: full frame discrete cosine transform (DCT) with entropy coding and Laplacian pyramid hierarchical coding (LPHC). The dependence of their efficiency on the compression parameters was investigated. The techniques were compared in terms of the trade-off between the bit rate and the detection accuracy of subtle microcalcifications by an automated detection algorithm. The mean-square errors in the reconstructed images were determined and the visual quality of the error images was examined. It was found that with the LPHC method, the highest compression ratio achieved without a significant degradation in the detectability was 3.6:1. The full frame DCT method with entropy coding provided a higher compression efficiency of 9.6:1 at comparable detection accuracy. The mean-square errors did not correlate with the detection accuracy of the microcalcifications. This study demonstrated the importance of determining the quality of the decompressed images by the specific requirements of the task for which the decompressed images are to be used. Further investigation is needed for selection of optimal compression technique for digital mammograms.     

A Cost-Effective Thickness Measurement Technique for Engine Propellers

This paper describes the design and development of a precision calliper system to measure the surface profile of an outboard marine engine propeller blade. Several instruments that are commonly used for measuring the surface profile of a propeller blade are reviewed in this paper. These include the pitch meter, the profilometer and the computer numerical control coordinate-measuring machine (CNC-CMM). However, the operating practices and availability of different facilities in industry necessitate a more cost-effective approach. An alternative method using a precision calliper system is therefore proposed. Details of the design criteria, principles of operation and the testing and verification of the system are presented. The paper concludes that the precision calliper system is a cost-effective method for measuring the surface profile of a propeller.