Search

Hashing code similarity search is an effective method for large-scale image retrieval, since it provides fast search calculating and memory operating. In image retrieval, hash code based on deep convolutional networks can learn accurate image semantic information and compact hash code simultaneously. The existing methods generally extract the overall features of the image and generate corresponding hash codes. When the image contains multiple targets, this method may be suboptimal for describing the image, thus, limiting the accuracy of multi-label images. This paper focuses on the use of deep convolutional hash coding for multi-label image problems. In order to solve this problem, the authors propose a deep convolutional neural network structure suitable for multi-label image feature extraction. This network can also be used for end-to-end feature learning and further improve image retrieval accuracy. In this method, each target in the image is represented by a hash code and extensively evaluated across multiple data sets, making substantial improvement over the most advanced supervised and unsupervised hashing methods.

It is difficult to accurately segment the tongue due to the blurred contours and the similar colors of the surrounding tissue. This paper presents a semantic segmentation method for tongue body based on fully convolutional neural network. First, the convolutional and pooling layers are used to map the tongue image from the pixel domain to the feature domain. Then, the deconvolutional layer is used to restore the shrinking feature image to the original size. Finally, the Softmax classifier is trained to classify each point of the image in order to achieve segmentation. Experimental results show that the method proposed in this paper can get better segmentation results, laying a solid foundation for tongue analysis and dialectical diagnosis.

The resist filling behavior is crucial to the quality of the final imprinted patterns in microimprint lithography. To achieve the microscale velocity field of resist, a 3-D defocusing digital particle image velocimetry (DDPIV) system was established. The spatial coordinates of 500 nm fluorescent tracer particles were inferred from their DDPIV images generated by a mask with three apertures forming an equilateral triangle. Time-resolved 3-D particle field inside the resist was obtained with the spatial coordinates of particles. Particle tracking velocimetry was utilized to derive the velocity field from the particle spatial position in the imprinting sequence. Velocity history of particles along the extracted track was described. The results showed that the maximum velocity of the resist was always located in the region between the mold corner and the supporting substrate; meanwhile, the velocity component of the resist in the vertical direction is approximate to zero. The volume transfer characteristics of resist was illustrated from the view of particle field and velocity field, which will help reveal the resist filling mechanism and provide useful guidance for the mold structure optimization.

On the basis of analyzing flaws of the traditional means of traffic accident scene survey and inadequate of the existing photogrammetry technique, this paper presents a panoramic stereo photogrammetry technology applying to traffic accident survey. By employing the result of photogrammetry, the drawing module can automatically draw traffic accident scene diagrams for the accident analysis and reconstruction, so as to quickly achieve the purpose of measurement and drawing.Experiments show that the presented accident scene coordinate-machine can measure the distance and the azimuth of all the relevant objects on the accidental scene, and enjoys the advantages of high precision in measurement, convenience in operation and carry, no necessity in calibration,etc. So it can meet the traffic police's needs of the measurement and drawing of the traffic accident scene.

The traditional slicing method of reverse engineering has been used in product measure from time immemorial. This method however has the disadvantage of low contrast of the cross-sectional pictures of an object. In order to overcome the said shortcoming, a new slicing method of reverse engineering, based on the principle of refraction and reflection of a prism, has been propounded. According to the reflectivity of the object, one of the illuminating methods—straight illuminating or inclined illuminating—is adopted. These methods can enable one to obtain the image of the cross-section of a bright object with a dark background or the opposite. Experiments have proved to show the advantages of this new slicing method for high contrast of the cross-sectional pictures. To eliminate geometrical distortions caused by the refraction and reflection of the prism, a mathematical transformation model can be set up to correct the image by using relevant software. Eventually, a RP model of a temporomandibular joint fabricated according to its slicing pictures is illustrated.

In order to build the complex built-in labyrinth design of an emitter which is a key element in water-saving devices, rapid prototyping and manufacturing (RPM rapid tooling (RT) for the emitter has been fabricated using a metal spraying process to carry out trial-production. Finally, with the fabrication ofa precision mould as the basis, emitter mould design and manufacturing have been completed. As a result, the integration of design/verification/manufacturing of a mould and its products is realised.

A cutter layout optimization strategy for full-face rock tunnel boring machine (TBM) is proposed, to overcome the drawback that the original design usually can not meet the balance requirements for cutter head forces and the rock breaking amount of each cutter. The layout schemes are designed by grouping the cutters and exerting micro-adjustment for the position angle and radius. The best layout is achieved by selecting the layout schemes using grey relational analysis and the TB880E TBM cutter layout are optimized. Compared with the computational results of the original layout design, the eccentric moment decreases by 65%. It is concluded that the position angle plays a main role in cutter layout optimization, and the cutter layout exerts obvious influence on cutter head performance. The optimization strategy can avoid stress concentration without doing harm to structural stiffness.

For the on-line measurement of the fabric color in the batch dyeing process, a novel method is proposed based on soft-sensor. In this method, the concentrations of the dyestuff in a jet dyeing machine are selected as the soft sensor's inputs, and the the fabric color is the output. A nonlinear model, which relates the absorbance with the concentrations of the dyestuff, is obtained based on the experiments and the regression analysis method. Using this nonlinear model, the concentrations of the dyestuff during the dyeing process are measured by the extended Kalman filter(EKF). Further, the soft-sensing model is proposed to predict the fabric color by the obtained concentrations of the dyestuff. The numerical results for the soft-sensing method of color measurement in the dyeing process of knitted cotton using reactive dyes are compared to the experimental results, leading to good agreement between theory and experiment. This demonstrates that this soft-sensing model is able to predict the fabric color in the textile industries for the batch dyeing process.

The image feature matching is a critical step in photography measurement and rebuilding. Based on the Characteristics of topography measurement, a new topography feature matching algorithm is presented in this paper. In the algorithm, the stereo images to be matched are partitioned, and then the region matching process is used to these partitioned image pairs. Based on the region matching, the corner feature matching operation is then processed, which involves relaxed iteration algorithm, zero-crossing method and least squares median algorithms to eliminate the ill matching points. Three groups of topography photography measurement images are used in image matching experiment, the experiment results shows that this algorithm can effectively improve the computation efficiency and matching accuracy, thus has a wide applications in the area based on the principle of stereo vision, such as: topography photography measurement, urban planning, etc.

In the real-time panoramic images processing, omni-directional vision sensors (ODVS) is a fast and reliable means of visual information collection, but current ODVS have a dead angle. According to the average angular resolution for two-catadioptric ODVS imaging theory, a new design of ODVS structure and catadioptric mirror is presented in this paper to overcome the defect. The reflectors curvilinear numeric solutions of this catadioptric mirror is obtained by the fourth order Runge-Kutta algorithm, and the dead angle part of the panoramic images that normal ODVS canpsilat acquire is acquired by a combine-lens of a wide-angle lens and a normal ODVS. The experimental results show that the ODVS presented in this paper can achieve a true omni-directional surveillance, and have a good applicational value in the fields such as intelligent omni-directional video surveillance, dynamic image understanding and computer vision.

In order to achieve the real-time, convenient, automatic and intelligent 3D vision measurement, this paper proposes a 3D vision measurement method based on binocular omni-directional vision sensor (ODVS), which can get the 3D panoramic image in real-time, this paper considers the human eyes as the center of vision space. At the process of gathering, processing, describing and expressing of data, this paper adopts a kind of uniform coordinate based on Gauss spherical coordinates, adopts a kind of design using ODVS having average angle resolution, and combines two ODVS having the same parameters into one. In this paper, we present the design method and experimental results. The experimental results indicate that our research results, can simplify the complexity of 3D visionpsilas measurement, can make feature extraction more convenient, can make the realization of the match of 3D images easier, and finally achieves a 3D vision measurement which is high efficient, real-time and accurate. The paper has important value on stereoscopic 3D measurement and 3D image reconstruction.

To effectively realize the image feature matching for geomorphic reverse measurement and rebuilding, a new matching scheme is presented, where the SIFT method are adopted to implement initial geomorphic image matching by going through five stages: scale-space construction, scale-space extrema detection, orientation assignment, keypoint descriptor and feature vector matching. Then, in order to eliminate the wrong matching features existing in the initial matching process, RANSAC algorithm is applied. The experimental results show that this algorithm can effectively improve the accuracy and efficiency of geomorphic image matching.

For existing three-dimensional (3D) laser scanners, acquiring geometry and color information of the objects simultaneously is difficult. Moreover, the current techniques cannot store, modify, and model the point clouds efficiently. In this work, we have developed a novel sensor system, which is called active stereo omni-directional vision sensor (ASODVS), to address those problems. ASODVS is an integrated system composed of a single-view omni-directional vision sensor and a mobile planar green laser generator platform. Driven by a stepper motor, the laser platform can move vertically along the axis of the ASODVS. During the scanning of the laser generators, the panoramic images of the environment are captured and the characteristics and space location information of the laser points are calculated accordingly. Based on the image information of the laser points, the 3D space can be reconstructed. Experimental results demonstrate that the proposed ASODVS system can measure and reconstruct the 3D space in real-time and with high quality.

One of the most important aspects of Gerontechnology is to support the elder who lives alone at home. According to the elder's relatively obvious and stable routine of daily activities, this paper proposes a statistical approach based on machine vision to build an Elder Indoor and Outdoor Activity Model (EIOAM) through analysis of the elder's daily activity data in the main activity places and the entry/exit places collected by the Omni-directional Vision Sensor (ODVS). Since the elder's daily routine varies with the alternating of seasons and growing of age, the model should learn the routine of activities adaptively. This model is able to detect and predict the abnormal activities of the elder through detecting the significant deviations of the activity data in spatial and temporal aspects. By using this model, one can not only detect the abnormal activities happened in sight of the vision sensor (indoor), but also out of sight (outdoor). Thus provides a new methodology for the remote home care of the elder who lives alone.

Omni-directional vision sensor (ODVS) is one of important components of sensor networks. Design of ODVS, embedded Linux ODVS, video server of ODVS, and software development of ODVS applications are studied in this paper. In addition, the applications of multi-object automatic tracking systems based on ODVS are described in details. Moreover, experimental results are proposed. This research is significant for sensor networks to be efficiently and effectively implemented.

China is running to the aging society. In China, the number of the elder’s families of empty nest presents an ascendant trend. It has caused various kinds of demands of the service for spiritual consolation. This article introduces how to distinguish different emotion form the sound sample by affective computing and brings forward the concept of spiritual consolation object. Elder can communicate with this object when they need spiritual consolation. With this, we can set up an interchange environment considering people first, which is intelligent and understandable between children and the elder.

Water quality monitoring is of great importance in water safety protection and water emergency supervision. Water quality can be reflected by aquatic creatures' ecological status, especially fish's, directly and synthetically. Therefore, aquatic creatures' ecological status can be used to monitor water quality safety. This paper presents an real-time water quality monitoring technology in which computer image processing technique, network communication technique and observation of aquatic creatures' ecological status, such as small fish's, technique are used. A machine vision based biological water quality monitoring equipment is proposed. It monitors water quality safety by observing fish's biological status. This new water quality monitoring technology overcomes the shortages of existing water quality monitoring technology, which is costly, and inapplicable to large-scale long-term and on-line water quality monitoring. Thus, it provides an economical and effective method for water quality monitoring, water safety protection and water emergency supervision.

The resist filling behavior is crucial to the quality of the final imprinted pattern in micro/nanolithography. To obtain resist flow fields, a three-dimensional (3-D) defocusing digital particle image velocimetry (DDPIV) system was set up to realize the visualization of the resist filling process. Three-dimensional motion trajectories and velocity vectors of tracer particle sets were calculated to characterize this microscale flow phenomena. The results show that the particles’ maximum velocity is located in the region below the mold corner, and the region leans to the mold cavity. Meanwhile, the squeezed resist will first move along the mold moving direction, and then fills the mold cavity in an upward moving tendency when it passes through the mold corner. The feasibility of using the DDPIV system to investigate the resist filling behavior was confirmed. The results will help to understand the resist filling behavior and provide useful instruction for the selection of process parameters and mold structure optimization.

In microimprint lithography, the resist deformation directly influences the quality of the final imprinted patterns. The resist velocity field was investigated through numerical simulations and visualization experiments. A numerical model based on the computational fluid dynamics was built to predict the resist filling behavior. Meanwhile, a 3D defocusing digital particle image velocimetry (DDPIV) system was developed to achieve the microscale velocity field of resist. The spatial coordinates of the fluorescent tracer particles were derived from their defocused images, and then the three-dimensional particle field and velocity field inside the resist were obtained according to the particles' spatial coordinates and time interval recording the particle images. The investigation of the velocity field, including the horizontal and vertical velocity history, was performed to help describe the filling mode and flow behavior of the resist. The experimental results agreed well with the simulation prediction, which justified the use of the micro DDPIV system to investigate the resist filling behavior and verified the numerical model. The combined effect of the mold's local asymmetric geometries and resist's initial thickness on its own deformation was further analyzed by numerical simulation.