34 results about "Lateral inhibition" patented technology

A parallel dynamical system for computing sparse representations of data, i.e., where the data can be fully represented in terms of a small number of non-zero code elements, and for reconstructing compressively sensed images. The system is based on the principles of thresholding and local competition that solves a family of sparse approximation problems corresponding to various sparsity metrics. The system utilizes Locally Competitive Algorithms (LCAs), nodes in a population continually compete with neighboring units using (usually one-way) lateral inhibition to calculate coefficients representing an input in an over complete dictionary.

The invention discloses an adaptive image target enhancement method based on a difference of Gaussian model and belongs to the digital image processing field. In the method, based on a lateral inhibition phenomenon of a biological visual receptive field, the difference of Gaussian (DOG) model of image space domain filtering is established. Target and noise gray level distribution prior knowledge in a water surface image and a constraint relation of excitability and inhibition effect offset are used to select a model parameter so as to reach a local optimal enhancement effect. By using the method in the invention, comprehensive performance of target enhancement, background inhibition and noise filtering is better than the comprehensive performance of a traditional spatial-domain high pass filter. The enhanced image possesses a good visual sense and simultaneously a demand of subsequent motion vector estimation to a correlation operation signal to noise ratio is satisfied.

The invention provides a digital image enhancement method based on an optic nerve network. The method comprises the following steps: S1, acquiring the image intensity of an image to be processed and compressing the image intensity within the dynamic range to obtain a compressed image; S2, extracting the contrast ratio of the image to be processed; and S3, modulating and uniting processing the compressed image according to the contrast ratio so as to obtain an enhanced image. The S1 and S2 are in no particular order. The digital image enhancement method achieves the purpose of completing image enhancement through combination of a lateral inhibition nerve network and a Weber code for describing the response of retina cone cells, and solves the problems of both color permanence and dynamic range compression mentioned in the prior art.

Provided is a neuromorphic system using a neuron circuit. The neuromorphic system includes: one or two or more neuron circuits configured to output a firing signal according to signals input from a synapse array; a homeostatic circuit for each neuron circuit; and a global self-controller configured to generate and provide control signals for the neuron circuits by using the firing signal output from the neuron circuits. The neuron circuit includes a neuromorphic device and an output circuit that outputs the firing signal of the neuromorphic device. The global self-controller generates and supplies a reset signal to the neuromorphic device of the fired neuron circuit, and the global self-controller generates and supplies a lateral inhibition signal to the neuromorphic device of the non-fired neuron circuit. The homeostatic circuit alleviates inhibition of other neurons by the neurons with a predominant firing function.

The invention provides an improved top speed learning model and a method for classifying modes of the top speed learning model, discloses an efficient neural network rapid learning method and a limited top speed learning machine and belongs to the field of mode identification and machine learning. The improved top speed learning model comprises (1) a concept of a limited parameter space, (2) a hypersphere limited condition in the limited parameter concept and (3) output weight learning. According to the concept of the limited parameter space, a lateral inhibition mechanism based on sample prior information is adopted and the content is particularly shown on the aspect of generation of a connection weight from an input layer to a hidden layer; according to the hypersphere limited condition in the limited parameter concept, selection of the connection weight from the input layer to the hidden layer is limited to a hypersphere; according to output weight learning, after a weight of the hidden layer is selected from the limited parameter space, learning is trained through a top speed learning machine model based on least squares, and finally an output weight of the model is obtained. According to the method, the classification and identification effects of the model can be greatly improved, and the training speed can be greatly increased.

The invention discloses a device and method for realizing short-cut nitrification-anaerobic ammonia oxidation based on lateral inhibition of hydroxylamine and belongs to the field of urban sewage treatment. Short-cut nitrification is realized in a treatment way that nitrite-oxidizing bacteria (NOB) is inhibited by using hydroxylamine, so that stable nitrite is provided for subsequent anaerobic ammonia oxidation. Hydroxylamine serving as a key intermediate product of a nitrification reaction plays a connecting role for the balance of the whole nitrification process, so that the aims of increasing the cell yield of ammonia oxidizing bacteria (AOB) and inhibiting the activity of NOB can be achieved by appropriately adding hydroxylamine, and furthermore, stable short-cut nitrification is realized. However, hydroxylamine has toxicity, and therefore, AOB and NOB can simultaneously lose activity if hydroxylamine is excessively added. Therefore, the excess problem can be controlled by lateralsludge treatment of hydroxylamine in the patent, meanwhile, short-cut nitrification can be relatively rapidly started, and relatively high nitrite accumulation can be maintained. The method is simplein operation and solves the problem that nitrite is difficult to stably maintain if urban sewage is treated by using a short-cut nitrification-anaerobic ammonia oxidation process.

The invention discloses an image edge grading-detection method based on visual pathway orientation sensitivity. A first neural network sensitive to multiple specific directions is established under the action of neuron synaptic connection on receptive field optimal orientation centripetal distribution, an image pixel is taken as network input, a pulse firing sequence of neuron in a certain time window is recorded, and a discharge frequency is calculated to serve as network output; network output in multiple directions is integrated and mapped to a gray scale, and an edge sensitive image is formed; as for the edge sensitive image, the inner lateral inhibition range and the inhibition quantity of a receptive field are determined, a second neural network is formed, and the laterally inhibited image is output; finally, an edge detection result is acquired after threshold processing. According to the method, important vision mechanisms such as directional receptive field, lateral inhibition and the like are considered, the grading processing effect of different levels of structures on a visual pathway during profile sensing is simulated, and the edge detection performance of a long-scale contrast image is improved.

The invention relates to a method for detecting weak edges of images on the basis of discharge information of multilayer neuron groups. The method includes constructing the multilayer neuron groups with interconnected inhibitory synapses, inputting digital images into input-layer neuron groups and representing image pixels by the time-space information of first discharge of various neurons; describing space details of the images by time variances by the aid of visual receptive fields and discharge time sequences of the various neurons, selecting attentive mechanisms in the consideration of lateral inhibition so as to acquire visual attention data of information of the images; implementing space variable-resolution mechanisms on the basis of a combination of selective attention procedures by the aid of Log-Gabor multi-direction filter results, acquiring reconstructed information of the edges of the images and reinforcing the information of the edges of the images by the aid of output-layer neuron groups. The method has the advantages that a synapse interconnection characteristic of the neuron groups is taken into consideration; simple visual information procedures of cortices are reflected by the aid of multi-direction filter mechanisms; the weak edges of the images can be effectively detected by the aid of the multilayer neuron groups.

The invention relates to an image matching method based on lateral inhibition and chaos quantum particle swarm optimization, comprising the following steps of: (1) pre-processing images by using lateral inhibition principles, and extracting image edges; (2) initiating each parameter of particle swarm optimization; (3) calculating the fitness value of each particle; (4) comparing the fitness valueof each particle of the cycle, i.e. the kth cycle, and the fitness value of each particle obtained from the former step, wherein the maximal fitness value is the global optimization gbest; simultaneously comparing the fitness value of each particle obtained from the former step respectively with the fitness value of the particle obtained in the (k-1)th cycle, wherein the greater fitness value is the optimization Pbest of the particle self of the kth cycle; (5) carrying out particle swarm optimization according to the fitness values of the particles; (6) skipping to the step 3 when the currentcycle time plus 1, repeating the operation till the cycle time is greater than the maximum cycle time N; and (7) ending the operation and outputting the optimized allocation position and the optimized fitness value.

The invention relates to an infrared image processing method based on a lateral inhibition network. The method comprises the following steps that S1, partial entropy in each pixel point region of an image is calculated so that a partial entropy matrix of the image can be obtained; S2, according to the partial entropy matrix of the whole image, a maximum value of the matrix is calculated and then a measurement operator is constructed; S3, an inhibition coefficient matrix is solved; S4, according to the results obtained through the S2 and the S3, the infrared image is processed and lateral inhibition network output is obtained. According to the different characteristics of an image saltation zone (including edges and details) and a smoothness zone (including backgrounds and noise) in an empty region, the measuring operator is constructed through the image partial entropy. Therefore, the lateral inhibition network has the capacity of edge identification and is strong in noise immunity. After the lateral inhibition network is combined with a filtering mechanism, the image is enhanced and the lateral inhibition network has the noise inhibiting effect.

The invention provides a system and a method of fusion of an infrared-radiation (IR) image and a low-light-level (LLL) color image. According to the system and the method, lateral inhibition enhancement (LTE) is carried out on the infrared image and the low-light-level image to acquire an IR image and an LLL image; the IR image is pre-processed to acquire a partial image T; weighting and calculation are carried out on the LLL image and the T image to acquire an LLL' image; the LLL' image is processed to acquire a +LLL' image; and the IR image is processed to acquire a -IR image; the -IR imageenters a surrounding region of an ON module, the +LLL' image enters a center region of the ON module, and an image after fusion is acquired; and a red channel, a green channel and a blue channel are respectively adopted to carry out mapping on the fusion image, the +LLL' image and the -IR image. According to the system and method, a bionic biological visual ON-OFF model is adopted, the infrared-radiation image passing through an OFF system and the low-light-level image passing through an ON system are respectively input into an inhibition area and an excitement area of the ON system, and the fusion image which accords with human eye vision, is clear in a target, and is rich in background details is obtained.

The invention relates to a lateral inhabitation coefficient determining method based on unilateral attenuation exponential and belongs to the field of image enhancement processing. A lateral inhibition coefficient distribution function is based on the unilateral attenuation exponential, the size of the radius N of a lateral inhibition field range is used for determining a coefficient sigma, the lateral inhibition coefficient is distributed and concentrated in a small lateral inhibition field range through controlling the lateral inhibition coefficient attenuation speed rate to reduce calculation amount of a lateral inhibition network, and a coefficient A is determined based on the optimal lateral inhibition coefficient and the sigma to effectively enhance image visual effects. The method is simple in implementation process, small in calculation amount and obvious in image enhancement effect, and has application and popularization value.

The invention discloses a probabilistic neuron circuit, and a probabilistic neural network topological structure and application thereof. The probabilistic neuron circuit comprises an integrating capacitor, a non-fixed threshold volatile device and a load resistor, wherein one end of the integrating capacitor is externally connected with a synaptic resistor and connected with one end of the non-fixed threshold volatile device, and the other end of the volatile device is connected with one end of the load resistor. The network topological structure comprises a plurality of input neuron circuits, a plurality of probabilistic neuron circuits and a lateral suppression neuron circuit, wherein each probabilistic neuron circuit is used for carrying out random excitation based on the non-fixed excitation threshold value of the probabilistic neuron circuit and an electric signal emitted by each input neuron circuit; and the suppression neuron circuit is used for suppressing the excitation of other subsequent probabilistic neuron circuits when receiving signals excited by the first n probability neuron circuits. According to the invention, the non-fixed threshold volatile device is introduced into the neuron circuit, so the application of the neuron circuit is greatly expanded, and the neuron circuit can be particularly used for solving non-deterministic problems and has a reliable solution result.

The invention relates to a background suppression method used for a gun-projectile remote control weapon station, and relates to the technical field of image processing. A visual bionics technology isapplied; a lateral inhibition mechanism of a visual system is introduced; according to image information, a measurement factor and a local range variance for describing edge characteristics of an image are introduced for determining long and short axis scales of an anisotropic Gaussian filter; and according to gradient information of the image, direction information of the filter is determined, so that the anisotropic Gaussian filter is constructed. The image information is associated with the determination of a lateral inhibition coefficient, so that an image information-based adaptive lateral inhibition network coefficient is determined, a conventional mode of adopting a fixed lateral inhibition coefficient template is improved, and high self-adaptability is achieved. Meanwhile, duringimage characteristic selection, the influence of a noise signal on a lateral inhibition network is considered, so that the anti-noise performance of the lateral inhibition network is improved to a certain extent.

The invention provides an infrared image and low-light-level image fusion system and method. According to the invention, lateral inhibition enhancement processing is performed on an infrared image anda low-light-level image to obtain an IR image and an LLL image, preprocessing is performed on the IR image to obtain a local image T, the LLL image and the T image are weighted and calculated to obtain an LLL' image, the LLL' image is processed to obtain a +LLL' image, the IR image is processed to obtain a -IR image, the -IR image enters a surrounding region of an ON module, the +LLL' enters a central region of the ON module, and a fused image is obtained. The infrared image and low-light-level image fusion system and method adopt a bionic biological vision ON-OFF model, and the infrared image passing through an OFF system and the low-light-level image passing through an ON system are respectively inputted into an inhibition region and an excitement region of the ON system, so that a fused image which conforms to the human eye vision and is clear in target and rich in background detail is obtained.

The invention discloses an image understanding method based on synergetics fluctuating force, which solves relevant problems in image understanding by utilizing the synergetics. The image understanding method based on the synergetics fluctuating force of the invention solves the relevant problems by inducting the potential function dynamical equation fluctuating force to effectively utilize prior knowledge, perfecting lateral inhibition items and adding a semantic polysemy attention parameter item to solve the problems of multiple targets and ambiguity targets, therefore, the relationship of mutual guidance and mutual driving between a scene and a target in the scene is reflected, and the system is changed into 'Everyone Takes Own Site' instead of 'Winner Takes All' only with one winner, thus finishing scene interpretation and target identification in the scene.

The present invention discloses a lateral inhibition random fractal search template coupling method. The method comprises: performing image preprocessing, obtaining an original image and a template image, and converting the original image and the template image to a gray level mode; utilizing the lateral inhibition mechanism to perform image processing, wherein the inhibition mechanism can effectively perform background inhibition and target enhancement so as to reduce the image noise and improve the signal to noise ratio; performing LI-SFS parameter initialization; setting the maximum number of diffusion times as 1; applying the Gaussian migration method to solve the template matching problem updating the position of a search individual; and obtaining an optimal individual after performing the update process twice. The lateral inhibition random fractal search template coupling method is compared with the algorithm based on the lateral inhibition, and the experiment result is shown in the template matching problem. The lateral inhibition random fractal search template coupling method has good effect and robustness, is greatly helpful to detect a target in the cluttered background, can enhance the comparison of the feeling information and reduce the low-frequency noise.

The embodiment of the invention discloses a hidden layer neuron adaptive activation method and device and terminal equipment applied to a memristor pulse neural network, each synapse in the memristorpulse neural network only comprises one memristor, and the method comprises the following steps: calculating an average input current according to the input current of each hidden layer neuron in thesame layer; injecting the average input current into each hidden layer neuron; controlling the hidden layer neurons of which the corresponding input current is greater than the average input current to discharge in sequence according to a preset discharge sequence rule; determining an activation value of each discharged hidden layer neuron according to the discharge sequence of each discharged hidden layer neuron; and correspondingly activating each discharged hidden layer neuron by utilizing the activation value. Lateral suppression between hidden layer neurons is realized; and each synapse can only comprise one memristor, so that the construction of a complex hardware connection network is avoided.