Online composite shape recognition based on relevance feedback

This paper describes a novel method of online composite shape recognition interms of the relevance feedback technology to capture a user's intentions incrementally, and adynamic user modeling method to adapt to various users' styles. First, the relevance feedback isadapted to refine the recognition results and reduce the ambiguity incrementally based on theestablishment of a feature-based vector model of a user's sketches. Secondly, a dynamic usermodeling is introduced to model the user's sketching habits based on recording and analyzinghistorical information incrementally. A model-based matching strategy is also employed in the methodto recognize sketches dynamically. Experiments prove that the proposed method is both effective andefficient.

Extraction of affine invariant features for shape recognition based on ant colony optimization

A new approach to extraction of affine invariant features of contour image and matching strategy is proposed for shape recognition.Firstly,the centroid distance and azimuth angle of each boundary point are computed.Then,with a prior-defined angle interval,all the points in the neighbor region of the sample point are considered to calculate the average distance for eliminating noise.After that,the centroid distance ratios（CDRs） of any two opposite contour points to the barycenter are achieved as the representation of the shape,which will be invariant to affine transformation.Since the angles of contour points will change non-linearly among affine related images,the CDRs should be resampled and combined sequentially to build one-by-one matching pairs of the corresponding points.The core issue is how to determine the angle positions for sampling,which can be regarded as an optimization problem of path planning.An ant colony optimization（ACO）-based path planning model with some constraints is presented to address this problem.Finally,the Euclidean distance is adopted to evaluate the similarity of shape features in different images.The experimental results demonstrate the efficiency of the proposed method in shape recognition with translation,scaling,rotation and distortion.

Improvement of Shape Recognition Performance of Sendzimir Mill Control Systems Using Echo State Neural Networks

High rigidity twenty-high Sendzimir mills （ZRMs） are widely used for rolling stainless steels, silicon sheets, etc. A ZRM uses a small diameter work roll to produce massive rolling forces. Since a work roll with a small diameter can be bent easily, strips often have complex shapes with mixed quarter and deep edge waves in the shape of plates. In order to solve this problem, fuzzy neural network controls are generally used for shape： recognition in ZRM control systems. Among various neural network types, the multi-layer perceptron （MLP） is typically used in current ZRMs. However, an MLP causes the loss of a large amount of shape recognition data. To improve the shape recognition per- formance of ZRM control systems, echo state networks （ESNs） are proposed to be used. Through simulation re- sults, it is found that shape recognition performance could be improved using the proposed ESN method.

Fourier Descriptors with Different Shape Signatures:a Comparative Study for Shape Based Retrieval of Kinematic Constraints

Fourier Descriptors（FD） has been widely used in image analysis and computer vision for shape recognition as they can be made independent of translation,rotation,as well as scaling.They have also been used for developing methods for the analysis and synthesis of four-bar linkages for path generation.This paper focuses on a comparative study of Fourier descriptors derived from various shape signatures of planar closed curves.This includes representations based on Cartesian coordinates,centroid distance,cumulative angle,and curvature.The comparison is conducted not only using commonly used criteria for shape representation and identification but also in the context of shape based retrieval of kinematic constraints for task centered mechanism design.Examples are provided to seek to extract geometric constraints such as circle,circular arc,ellipse and line-segment from a given motion.

Application of Integrated Database to the Casting Design

Construction of integrated database including casting shapes with their casting design, technical knowledge, and thermophysical properties of the casting alloys were introduced in the present study. Recognition tech- nique for casting design by industrial computer tomography was used for the construction of shape database. Technical knowledge of the casting processes such as ferrous and non-ferrous alloys and their manufacturing process of the castings were accumulated and the search engine for the knowledge was developed. Database of thermophysical properties of the casting alloys were obtained via the experimental study, and the properties were used for the in-house computer simulation of casting process. The databases were linked with intelligent casting expert system developed in center for e-design, KITECH. It is expected that the databases can help non casting experts to devise the casting and its process. Various examples of the application by using the databases were shown in the present study.

MVContrast:Unsupervised Pretraining for Multi-view 3D Object Recognition

3D shape recognition has drawn much attention in recent years.The view-based approach performs best of all.However,the current multi-view methods are almost all fully supervised,and the pretraining models are almost all based on ImageNet.Although the pretraining results of ImageNet are quite impressive,there is still a significant discrepancy between multi-view datasets and ImageNet.Multi-view datasets naturally retain rich 3D information.In addition,large-scale datasets such as ImageNet require considerable cleaning and annotation work,so it is difficult to regenerate a second dataset.In contrast,unsupervised learning methods can learn general feature representations without any extra annotation.To this end,we propose a three-stage unsupervised joint pretraining model.Specifically,we decouple the final representations into three fine-grained representations.Data augmentation is utilized to obtain pixel-level representations within each view.And we boost the spatial invariant features from the view level.Finally,we exploit global information at the shape level through a novel extract-and-swap module.Experimental results demonstrate that the proposed method gains significantly in 3D object classification and retrieval tasks,and shows generalization to cross-dataset tasks.

TGMin： A global-minimum structure search program based on a constrained basin-hopping algorithm

In this article, we introduce Tsinghua Global Minimum （TGMin） as a new program for the global minimum searching of geometric structures of gas-phase or surface-supported atomic clusters, and the constrained basin-hopping （BH） algorithm implemented in this program. To improve the efficiency of the BH algorithm, several types of constraints are introduced to reduce the vast search space, including constraints on the random displacement step size, displacement of low-coordination atoms, and geometrical structure adjustment after displacement. The ultrafast shape-recognition （USR） algorithm and its variants are implemented to identify duplicate structures during the global minimum search. In addition to the Metropolis acceptance criterion, we also implemented a morphology-based constraint that confines the global minimum search to a specific type of morphology, such as planar or non-planar structures, which offers a strict divide-and-conquer strategy for the BH algorithm. These improvements are implemented in the TGMin program, which was developed over the past decade and has been used in a number of publications. We tested our TGMin program on global minimum structural searches for a number of metal and main-group clusters including C60, Au20 and B20 clusters. Over the past five years, the TGMin program has been used to determine the global minimum structures of a series of boron atomic clusters （such as [B26]^-, [B28]^-, [B30]^-, [B35]^-, [B36]^-, [B39]^-, [B40]^-, [MnB16]^-, [COB18]^-, [RhB18]^-, and [TaB20]^-）, metal-containing clusters Lin （n = 3-20）, Aug（CO）8^＋ and [Cr6O19]^2-. and the oxide-supported metal catalyst Au7/γ-Al2O3, as well as other isolated and surface-supported atomic clusters. In this article we present the major features of TGMin program and show that it is highly efficient at searching for global-minimum structures of atomic clusters in the gas phase and on various surface supports.