Recently, many researchers have paid their more attention to image fusion technique based on pulse coupled neural network (PCNN). In order to make the researchers to rapidly understand the research development of image fusion basedonPCNN,itissystematicallyreviewedinthepaper.On the basis of statistical analysis on published papers, firstly, PCNN and some modified models are introduced. Then we review the PCNN's applications in the field of image fusion. Subsequently,someexistingproblemsaresummarized,while we give some suggestions for the future research.

Review of Image Fusion Based on Pulse-Coupled Neural Network

A method and an apparatus for detecting person to use a handle device are provided. The apparatus comprises an image capturing unit, a storing unit, and a processing unit. An image of the person is captured by the image capturing unit. The image and default mouth information is stored in the storing unit. The image is analyzed by the processing unit to obtain a face object. An ear side searching region and a mouth comparing region are determined by the processing unit according to the face object. Whether the person is using the handle device is determined by the processing unit searches whether a specific gesture is existed in the mouth comparing region and compares whether mouth action information detected in the mouth location region is conformed to the default mouth information, to determine whether the person is using the handle device.

Method and apparatus for detecting person to use handheld device

In this paper, neural network predictive control method is used to compensate the image forward motion of a certain aerial reconnaissance camera and we have solved several problems that traditional control methods have. Firstly, according to the principle of imaging, we analyzed the reasons for the existence of image forward motion and established the mathematical model. Secondly, we analyzed the theoretically feasibility of the method. At last, simulation, experiments and test are used to validate the practical feasibility. Through what we have done, we conclude that neural network predictive control method can be used to compensate image forward motion for this certain camera and can make a perfect performance.

Image Forward Motion Compensation Method for Some Aerial Reconnaissance Camera Based on Neural Network Predictive Control

The present invention discloses a method and device for identification of a blurred screen image. The method considers the blurred screen image feature: having repeated content, and the method comprises: determining whether the content of a single image has periodicity or not, if the content of the single image has periodicity, determining that the single image has the blurred screen image feature, and determining that the single image is a blurred screen image. The method employs a single image to complete the identification of whether the single image is the blurred screen image or not, and is convenient and rapid.

Method and device for identification of blurred screen image

The invention is applicable for the technical field of image processing, and provides a detection method and a detection device for concrete cracks based on space-time correlation The detection method comprises the following steps: carrying out video collection on a concrete structure to be detected to obtain at least two frames of images by video collection equipment, and sorting the collectionimages according to frame number so as to obtain an image sequence of the concrete structure to be detected; carrying out single-frame static crack detection on each frame of image in the image sequence of the concrete structure respectively to obtain candidate crack areas and candidate crack area information; according to the candidate crack area information, carrying out detection on the candidate crack areas based on a space-time correlated strategy to obtain a detection result; and according to the detection result, obtaining the crack marks of the concrete structure to be detected Through the embodiment, the crack detection result of a single static image is detected again, so that the problems of false alarm and crack detection leakage are effectively solved, and the reliability androbustness of the crack detection method are improved

Detection method and detection device for concrete cracks based on space-time correlation

Satellite automatic recognition device under complicated backgrounds

Being an efficient method of information fusion, image fusion has been used in many fields such as
machine vision, medical diagnosis, military applications and remote sensing. In this paper, Pulse Coupled Neural
Network (PCNN) is introduced in this research field for its interesting properties in image processing, including
segmentation, target recognition et al. and a novel algorithm based on PCNN and Wavelet Transform for
Multi-focus image fusion is proposed. First, the two original images are decomposed by wavelet transform. Then,
based on the PCNN, a fusion rule in the Wavelet domain is given. This algorithm uses the wavelet coefficient in
each frequency domain as the linking strength, so that its value can be chosen adaptively. Wavelet coefficients
map to the range of image gray-scale. The output threshold function attenuates to minimum gray over time. Then
all pixels of image get the ignition. So, the output of PCNN in each iteration time is ignition wavelet coefficients
of threshold strength in different time. At this moment, the sequences of ignition of wavelet coefficients represent
ignition timing of each neuron. The ignition timing of PCNN in each neuron is mapped to corresponding image
gray-scale range, which is a picture of ignition timing mapping. Then it can judge the targets in the neuron are
obvious features or not obvious. The fusion coefficients are decided by the compare-selection operator with the
firing time gradient maps and the fusion image is reconstructed by wavelet inverse transform. Furthermore, by this
algorithm, the threshold adjusting constant is estimated by appointed iteration number. Furthermore, In order to
sufficient reflect order of the firing time, the threshold adjusting constant αΘ is estimated by appointed iteration
number. So after the iteration achieved, each of the wavelet coefficient is activated. In order to verify the
effectiveness of proposed rules, the experiments upon Multi-focus image are done. Moreover, comparative results
of evaluating fusion quality are listed. The experimental results show that the method can effectively enhance the
edge details and improve the spatial resolution of the image.

Multi-focus image fusion algorithm based on adaptive PCNN and wavelet transform

Device for obtaining width of Moire fringe by using image processing technology

The invention relates to a method for eliminating cement crack interference in airport runway impurity detection. The method includes the following steps that a current frame image and a reference frame image are registered; the reference frame image and the current frame image are segmented a plurality of subregions, and differential operation is carried out on the registered current frame image and the corresponding subregion of the reference frame image; region energy of the differential subregion with high energy is marked as Vi; the position of the reference frame image keeps unchanged, the current frame image translates n pixels in the vertical direction and in the horizontal direction, and differential operation is carried out on the translated current frame image and the reference frame image, and differential energy is marked as Wi, n, wherein n is a natural number; if Wi,n/Vi is larger than 1.5, the position is a cement crack; and if Wi,n/Vi is smaller than or equal to 1.5, the position is an airport impurity. The method for eliminating cement crack interference in airport runway impurity detection is very effective, and by means of the method, the false alarm rate is obviously reduced during impurity detection.

Han Guangliang

Papers

Satellite automatic recognition device under complicated backgrounds

Multi-focus image fusion algorithm based on adaptive PCNN and wavelet transform

Device for obtaining width of Moire fringe by using image processing technology

Method for eliminating cement crack interference in airport runway impurity detection