Quantitative Analysis of X-ray Lithographic Pores by SEM Image Processing

Arrays of regular macropores in electronic, magnetic, photonic and sensing devices can be patterned by X-ray lithography. Such structures inevitably contain some irregularity and require time-consuming pattern inspections. In this work, a pattern inspection by intensity-based digital image processing procedure is proposed and tested on scanning electron microscopy images of porous SU-8 polymer resist. The Otsu’s thresholding converted grayscale to binary images and the closing morphology algorithm was applied to reduce noise in the images. The Canny edge detector was used to identify the contour of each pore by detecting abrupt intensity changes in the binary image. Pores were detected and their sizes were subsequently evaluated. The morphological distributions analyzed by this procedure are comparable to those carried out by the one-by-one human inspection.     

A New Learning Algorithm for the Fusion of Adaptive Audio–Visual Features for the Retrieval and Classification of Movie Clips

This paper presents a new learning algorithm for audiovisual fusion and demonstrates its application to video classification for film database. The proposed system utilized perceptual features for content characterization of movie clips. These features are extracted from different modalities and fused through a machine learning process. More specifically, in order to capture the spatio-temporal information, an adaptive video indexing is adopted to extract visual feature, and the statistical model based on Laplacian mixture are utilized to extract audio feature. These features are fused at the late fusion stage and input to a support vector machine (SVM) to learn semantic concepts from a given video database. Based on our experimental results, the proposed system implementing the SVM-based fusion technique achieves high classification accuracy when applied to a large volume database containing Hollywood movies.     

Automatic machine interactions for content-based image retrieval using a self-organizing tree map architecture

In this paper, an unsupervised learning network is explored to incorporate a self-learning capability into image retrieval systems. Our proposal is a new attempt to automate recursive content-based image retrieval. The adoption of a self-organizing tree map (SOTM) is introduced, to minimize the user participation in an effort to automate interactive retrieval. The automatic learning mode has been applied to optimize the relevance feedback (RF) method and the single radial basis function-based RF method. In addition, a semiautomatic version is proposed to support retrieval with different user subjectivities. Image similarity is evaluated by a nonlinear model, which performs discrimination based on local analysis. Experimental results show robust and accurate performance by the proposed method, as compared with conventional noninteractive content-based image retrieval (CBIR) systems and user controlled interactive systems, when applied to image retrieval in compressed and uncompressed image databases.     

An interactive approach for CBIR using a network of radial basis functions

An important requirement for constructing effective content-based image retrieval (CBIR) systems is accurate characterization of visual information. Conventional nonadaptive models, which are usually adopted for this task in simple CBIR systems, do not adequately capture all aspects of the characteristics of the human visual system. An effective way of addressing this problem is to adopt a "human-computer" interactive approach, where the users directly teach the system about what they regard as being significant image features and their own notions of image similarity. We propose a machine learning approach for this task, which allows users to directly modify query characteristics by specifying their attributes in the form of training examples. Specifically, we apply a radial-basis function (RBF) network for implementing an adaptive metric which progressively models the notion of image similarity through continual relevance feedback from users. Experimental results show that the proposed methods not only outperform conventional CBIR systems in terms of both accuracy and robustness, but also previously proposed interactive systems.     

Automatic Optical Inspection of Solder Ball Burn Defects on Head Gimbal Assembly

Journal of Failure Analysis and Prevention - The detection of low-quality solder joints in hard disk drive manufacturing is a time-consuming, error-prone and costly process that is often performed...     

Strategies for unsupervised multimedia processing: self-organizing trees and forests

In this article, we explore a new family of neural network architectures that have a basis in self-organization, yet are somewhat free from many of the constraints typical of other well-known self-organizing architectures. Within this family, the basic processing unit is known as the self-organizing tree map (SOTM). We will look at how this model has evolved since its inception in 1995, how it has inspired new models, and how it is being applied to complex multimedia research problems in digital asset management and microbiological image analysis.