The Self-Organizing Map (SOM) algorithm has attracted a great deal of interest among researches and practitioners in a wide variety of fields. The SOM has been analyzed extensively, a number of variants have been developed and, perhaps most notably, it has been applied extensively within fields ranging from engineering sciences to medicine, biology, and economics. We have collected a comprehensive list of 5384 scientific papers that use the algorithms, have benefited from them, or contain analyses of them. The list is intended to serve as a source for literature surveys. The present addendum contains 2092 new articles, mainly from the years 1998-2002. We have provided a keyword index to help finding articles of interest, and additionally a modern automatically constructed variant of a thematic index: a WEBSOM interface to the whole article collection of years 1981-2000. The SOM of SOMs is available at http://websom.hut.fi/websom/somref/search.cgi for browsing and searching the collection.

Bibliography of Self-Organizing Map SOM) Papers: 1998-2001 Addendum

A convenient and effective binocular vision system is set up Gesture information can be accurately extract from the complex environment with the system The template calibration method is used to calibrate the binocular camera and the parameters of the camera are accurately obtained In the phase of stereo matching, the BM algorithm is used to quickly and accurately match the images of the left and right cameras to get the parallax of the measured gesture Combined with triangulation principle, resulting in a more dense depth map Finally, the depth information is remapped to the original color image to realize three-dimensional reconstruction and three-dimensional cloud image generation According to the cloud image information, it can be judged that the binocular vision system can effectively segment the gesture from the complex background

/pdf/gesture-recognition-based-on-binocular-vision-4030bzffbp.pdf

Gesture recognition based on binocular vision

This report adds over 1600 annotated references on the numerical characterization of topography, terrain modeling or geomorphometry, to a 1993 literature review and its first three updates. Erroneous references from the four earlier reports are corrected and many citations of historic interest are included; the cumulative archive is at 6000 entries. An introductory essay cites several hundred of the new entries. These are listed under various topic headings or referenced in brief discussions of several other areas of research, including terrain data and new parameters, neo-orometry, landslide-hazard mapping, Hack's Law, and early work on the mathematical representation of ridges and drainageways.

/pdf/a-bibliography-of-terrain-modeling-geomorphometry-the-gye90y2rco.pdf

A bibliography of terrain modeling (geomorphometry), the quantitative representation of topography: supplement 4.0

This paper describes a software architecture that allows image processing researchers to develop parallel applications in a transparent manner. The architecture's main component is an extensive library of data parallel low level image operations capable of running on homogeneous distributed memory MIMD-style multicomputers. Since the library has an application programming interface identical to that of an existing sequential library, all parallelism is completely hidden from the user.The first part of the paper discusses implementation aspects of the parallel library, and shows how sequential as well as parallel operations are implemented on the basis of so-called parallelizable patterns. A library built in this manner is easily maintainable, as extensive code redundancy is avoided. The second part of the paper describes the application of performance models to ensure efficiency of execution on all target platforms. Experiments show that for a realistic application performance predictions are highly accurate. These results indicate that the core of the architecture forms a powerful basis for automatic parallelization and optimization of a wide range of imaging software.

A Software Architecture for User Transparent Parallel Image Processing

An image recording method includes applying a reaction liquid onto an intermediate transfer member, applying an ink onto the reaction liquid on the intermediate transfer member, forming an intermediate image by applying a liquid composition containing a water-soluble polymer onto the reaction liquid and the ink on the intermediate transfer member, and transferring the intermediate image by bringing the intermediate image on the intermediate transfer member into contact with a recording medium and separating the intermediate image from the intermediate transfer member with the contact with the recording medium maintained. The intermediate image to be brought into contact with the recording medium has a temperature Tc higher than or equal to the glass transition temperature of the water-soluble polymer, and the intermediate image to be separated from the intermediate transfer member has a temperature Tr lower than the glass transition temperature of the water-soluble polymer.

Image processing method and image processing apparatus

We describe a general purpose environment for the development of parallel image processing/computer vision algorithms: PRIME (parallel image media processing environment). 'General purpose' here means that the environment is designed so as to be used on a variety of multi-processor systems ranging from tightly-coupled computers to loosely-coupled computers. The key point of the system is that it provides an architecture- independent programming environment for image processing and computer vision. We show the outline of PRIME, its implementation, and its preliminary performance evaluation.

Software platform for parallel image processing and computer vision

In this paper, a neural network model, the hypercolumn model (HCM), which is applicable to general image recognition, is proposed. The HCM is a combination model of hierarchical self-organizing maps (HSOM) and neocognitron (NC); it resolves the disadvantages of both the HSOM and the NC, and inherits all of the advantages of both models. The HSOM quantizes and nonlinearly maps an input space into a small dimensional feature map. Using this feature map, the HSOM can function as an unsupervised clustering method and can easily solve pattern recognition problems, which are hard for traditional linear methods or for multilayered perceptrons using the back-propagation learning method because of the complex shapes of the class boundaries. On the other hand, the NC is a multilayered network, in which layers to extract local features and layers to integrate shifted features alternate. Using this structure, the NC can reduce the dimensionality gradually and recognize shifted and scaled patterns. By combining the characteristics of the HSOM and the structure of the NC, the HCM can be made applicable to general image recognition problems which have high dimensional input data and in which the shapes of the class boundaries are quite complex because of the high abstraction level of the classification. © 2000 Scripta Technica, Syst Comp Jpn, 31(2): 49–61, 2000

Hypercolumn model: A combination model of hierarchical self‐organizing maps and neocognitron for image recognition

We present an appearance-based method for face recognition and evaluate its robustness against illumination changes. Self-organizing map (SOM) is utilized to transform the high dimensional face image into low dimensional topological space. However, the original learning algorithm of SOM uses Euclidean distance to measure similarity between input and codebook images, which is very sensitive to illumination changes. In this paper, we present Mahalanobis SOM, which uses Mahalanobis distance instead of the original Euclidean distance. The effectiveness of the proposed method is demonstrated by conducting some experiments on Yale B and CMU-PIE face databases.

Face recognition under varying illumination using Mahalanobis self-organizing map

Presents a shape and pose estimation method for 3D multi-part objects, the purpose of which is to easily map objects from the real world into virtual environments. In general, complex 3D multi-part objects cause unwanted self-occlusion and non-rigid motion. To deal with the problem, we employ multiple viewpoint time-varying sequences, since there is enough information to estimate the parameters in the sensory data. In our framework, to minimize the error between the selected image feature points and the estimated model parameters, we employ a model fitting procedure which can adaptively select corresponding pairs. We have demonstrated that our system works well both for single part objects and for multiple-part objects using real image data.

Tracking of 3D multi-part objects using multiple viewpoint time-varying sequences

This paper presents a shape and pose estimation method for 3D multi-part objects, the purpose of which is to easily map objects from the real world into virtual environments. In general, complex 3D multi-part objects cause undesired self-occlusion and non-rigid motion. To deal with the problem, we assume the following constraints:

Naoyuki Tsuruta

Papers

Software platform for parallel image processing and computer vision

Hypercolumn model: A combination model of hierarchical self‐organizing maps and neocognitron for image recognition

Face recognition under varying illumination using Mahalanobis self-organizing map

Tracking of 3D multi-part objects using multiple viewpoint time-varying sequences

Multi-part Non-rigid Object Tracking Based on Time Model-Space Gradients