Image processing method and device

Abstract

The present invention discloses an image processing method and device, wherein the method comprises: acquiring image information, and converting the image information into a transmittable image signal; converting the image signal into a spike signal through an oscillating artificial neuron device; encoding the spike signal to obtain a counting pulse; wherein the number of the counting pulses is used to characterize the size of the spike; inputting the counting pulse into a pulse coupled neural network for segmentation processing to obtain a segmented target image. The present invention can realize the spike coding function and visual perception function in the human brain visual system.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to an image processing method and device. Background Art

[0002] Human visual perception is an important part of the central nervous system, which gives the organism the ability to process visual information. The human visual perception system mainly consists of sensory cells that perceive visual signals, such as photoreceptors, and processing units that can convert the detected information into electrical peaks. The human visual perception system can simultaneously detect and process light information and then transmit it to various visual centers in the brain. This structure forms the basis of the combined sensing, preprocessing and encoding capabilities of the human visual system. In recent years, researchers have developed some dynamic visual systems based on traditional image sensors and transistor pixel circuits.

[0003] However, these systems are unable to fully realize the spike coding function in the human visual system. Summary of the invention

[0004] In view of the above problems, the present invention proposes an image processing method and device, which can realize the peak coding function and visual perception function in the human brain visual system.

[0005] In the first aspect, the present application provides the following technical solutions through an embodiment of the present application:

[0006] An image processing method, comprising:

[0007] Acquiring image information and converting the image information into a transmittable image signal;

[0008] Converting the image signal into a spike signal through an oscillating artificial neuron device;

[0009] Encoding the peak signal to obtain counting pulses; wherein the number of the counting pulses is used to characterize the size of the peak;

[0010] The counting pulses are input into a pulse coupled neural network for segmentation processing to obtain a segmented target image.

[0011] Optionally, encoding the peak signal to obtain a counting pulse includes:

[0012] converting the spike signal into a periodic electrical signal;

[0013] The periodic electrical signal is converted into counting pulses.

[0014] Optionally, the pulse coupled neural network includes: a first pulse coupled neural network and a second pulse coupled neural network; the step of inputting the counting pulses into the pulse coupled neural network for segmentation processing to obtain a segmented target image includes:

[0015] Inputting the counting pulse into the first pulse coupled neural network for segmentation to obtain a feedback electrical signal and a link signal;

[0016] The feedback electrical signal and the link signal are input into the second pulse coupled neural network for processing to obtain a target image.

[0017] Optionally, the second pulse coupled neural network is a simplified single-layer pulse coupled neural network of a two-dimensional local network.

[0018] Optionally, the step of inputting the feedback electrical signal and the link signal into the second pulse coupled neural network for processing to obtain a target image includes:

[0019] Based on U ij (n) = F ij (n)(1+βL ij (n))、E ij (n) = θ and Get the target image; where U ij (n) is the modulation field, F ij (n) is the feedback electrical signal, L ij (n) and link signal, β is the link signal weight, E ij is the dynamic threshold for triggering neurons, (i, j) is the coordinate of neurons, Y ij is the target image.

[0020] In the second aspect, based on the same inventive concept, the present application provides the following technical solution through an embodiment of the present application:

[0021] An image processing device, comprising:

[0022] An acquisition module, used for acquiring image information and converting the image information into a transmittable image signal;

[0023] A conversion module, used for converting the image signal into a spike signal through an oscillating artificial neuron device;

[0024] An encoding module, used for encoding the peak signal to obtain count pulses; wherein the number of the count pulses is used to characterize the size of the peak;

[0025] The segmentation module is used to input the counting pulses into a pulse coupled neural network for segmentation processing to obtain a segmented target image.

[0026] Optionally, the encoding module is specifically used to:

[0027] converting the spike signal into a periodic electrical signal;

[0028] The periodic electrical signal is converted into counting pulses.

[0029] Optionally, the pulse coupled neural network includes: a first pulse coupled neural network and a second pulse coupled neural network; the segmentation module is specifically used to:

[0030] Inputting the counting pulse into the first pulse coupled neural network for segmentation to obtain a feedback electrical signal and a link signal;

[0031] The feedback electrical signal and the link signal are input into the second pulse coupled neural network for processing to obtain a target image.

[0032] Optionally, the second pulse coupled neural network is a simplified single-layer pulse coupled neural network of a two-dimensional local network.

[0033] Optionally, the segmentation module is further specifically used for:

[0034] Based on U ij (n) = F ij (n)(1+βL ij (n))、E ij (n) = θ and Get the target image; where U ij (n) is the modulation field, F ij (n) is the feedback electrical signal, L ij (n) and link signal, β is the link signal weight, E ij is the dynamic threshold for triggering neurons, (i, j) is the coordinate of neurons, Y ij is the target image.

[0035] An image processing method and device provided in the implementation of the present invention obtains image information and converts the image information into a transmittable image signal; then, the image signal is converted into a spike signal through an oscillating artificial neuron device; the spike signal is then encoded to obtain a counting pulse; the number of counting pulses is used to characterize the size of the spike; further, the counting pulse is input into a pulse coupled neural network for segmentation processing to obtain a segmented target image. The entire process of the method of this embodiment can directly, continuously and in real time respond to image information, and generate different spike signals and counting pulses according to different effective inputs, and finally the output of the target image is realized after segmentation processing, and the segmentation and segmented output of the photoelectric information are realized, completing the spike coding function and visual perception function in the human brain visual system. The method of this embodiment can also promote the construction of artificial visual perception systems and pave the way for the development of bio-inspired photoelectric devices, light-driven robots and neuromorphic computing.

[0036] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0038] Figure 1 A flowchart of an image processing method provided by a first embodiment of the present invention is shown;

[0039] Figure 2 A schematic diagram of the structure of an exemplary sensory neuron in the first embodiment of the present invention is shown;

[0040] Figure 3 A schematic diagram of a peak signal under different light conditions in the first embodiment of the present invention is shown;

[0041] Figure 4 A schematic diagram showing an image processing method provided by a first embodiment of the present invention is shown;

[0042] Figure 5 A schematic structural diagram of an image processing device provided by a second embodiment of the present invention is shown. DETAILED DESCRIPTION

[0043] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0044] First embodiment

[0045] See also Figure 1 , shows a flow chart of an image processing method provided by the first embodiment of the present invention. The method comprises:

[0046] Step S10: Acquire image information, and convert the image information into a transmittable image signal.

[0047] In step S10, the image information represents the image being collected or acquired. In this embodiment, the image information can be collected by an image sensor, and after collecting the light signal, the image sensor converts the light signal into a transmittable and storable image signal.

[0048] Step S20: converting the image signal into a spike signal through an oscillating artificial neuron device.

[0049] In step S20, the image signal can be converted into a spike signal by oscillating the artificial neuron device. In this embodiment, the oscillating artificial neuron device can be connected in series with the image sensor to form a sensory neuron, such as Figure 2 As shown, A represents the light signal, B represents the pulse, C represents the image sensor, D represents the oscillating artificial neuron device, p The sensory neurons form a sensory neuron array to sense image information and obtain spike signals. The image sensor used is an ultraviolet sensor. Furthermore, a capacitor can be connected in parallel to the outside of the oscillating artificial neuron device, and a constant bias voltage can be applied to directly respond to the image signal obtained after the ultraviolet light input, and the image signal can be encoded into a spike pulse signal.

[0050] For example, the size of the parallel capacitor is 10nF, and the bias voltage applied is 3V to achieve the above functions and simulate the function of neurons. Since the image sensor will have different resistance states with different wavelengths of light input, that is, it will cause the effective input of the oscillating artificial neuron device to be different, so that the entire oscillation circuit will have different oscillation frequencies, which can be used as an artificial vision system to achieve response processing of ultraviolet light of different frequencies. Figure 3 As shown, Figure 3 The spike signals obtained after responding to ultraviolet light of different frequencies are shown in FIG. Figure 3(a) represents the spike signal under dark conditions (Dark); Figure 3 (b) represents the peak signal under the condition of ultraviolet light wavelength λ = 365nm; Figure 3 (c) represents the peak signal under the condition of ultraviolet light wavelength λ=254nm; Figure 3 (d) shows the peak signal under the condition of ultraviolet light wavelength λ=365,254nm; the horizontal axis of the image is time and the vertical axis is voltage.

[0051] Step S30: Encode the peak signal to obtain counting pulses; wherein the number of the counting pulses is used to characterize the size of the peak.

[0052] In step S30, the specific encoding process includes: converting the spike signal into a periodic electrical signal; then, converting the periodic electrical signal into a counting pulse. The number of counting pulses is used to represent the peak size of the spike signal, and the larger the number, the larger the corresponding peak. Specifically, the specific method of encoding the spike signal can be encoded using an existing encoder that can perform the above process.

[0053] Step S40: inputting the counting pulses into a pulse coupled neural network for segmentation processing to obtain a segmented target image.

[0054] In step S40, the pulse coupled neural network includes: a first pulse coupled neural network and a second pulse coupled neural network. The first pulse coupled neural network is used to perform feature segmentation on the counting pulses formed after encoding, and after segmentation, it is mapped into a spike sequence corresponding to the counting pulses, including a feedback electrical signal and a link signal. The second pulse coupled neural network is used to process the feedback electrical signal and the link signal obtained after segmentation to obtain a target image.

[0055] The specific steps are as follows:

[0056] First, the counting pulse is input into the first pulse coupled neural network for segmentation to obtain feedback electrical signals and link signals; the first pulse coupled neural network is an existing pulse coupled neural network, that is, a neural network model simplified based on experimental observations in the visual cortex of cats and monkeys, which can be directly applied and will not be described in detail. Then, the feedback electrical signal and link signal are input into the second pulse coupled neural network for processing to obtain the target image. The second pulse coupled neural network is a simplified single-layer pulse coupled neural network of a two-dimensional local network. Among them, the two-dimensional network means that the constructed neural network is two-dimensional; local, relative to remote, usually means that there is no need to use a remote supercomputer, and only local processor calculations can be achieved, which shows that the constructed neural network is relatively simple and does not require a lot of computing resources. Single layer, relative to double or multi-layer, indicates that there is only one layer of pulse coupled neural network. Specifically, the pulse coupled neural network: divided into three layers: input domain, coupling connection domain, pulse generator. When a neuron is stimulated and responds, it will stimulate the adjacent neurons. This stimulation can help the surrounding neurons to respond, thereby forming a cluster of synchronous oscillation pulses.

[0057] In this embodiment, the feedback electrical signal and the link signal are input into the second pulse coupled neural network for processing to obtain the target image, which specifically includes the following implementation process:

[0058] Based on U ij (n) = F ij (n)(1+βL ij (n))、E ij (n) = θ and Get the target image; where U ij (n) is the modulation field, F ij (n) is the feedback electrical signal, L ij (n) and link signal, β is the link signal weight, E ij is the dynamic threshold for triggering neurons, (i, j) is the coordinate of neurons, Y ij is the target image. That is, the input neuron of the second pulse coupled neural network receives F ij (n), L ij (n) These two types of input signals. ij (n) = S ij , under external stimulation, S ij It is used to feedback the position of sensory neurons (i, j) in the pulse coupled neural network and serves as the input signal F ij (n) in the form of a pulse-coded UV image matrix with four different frequencies from sensory neurons. L ij (n) is used to receive the local stimulus Y generated in the nth iterative calculation processkl (n-1) and L ij (n-1). Among them, Y kl (n-1) is the excited state of neuron (k, l) in the (n-1)th iteration, α L is the error time constant of the link channel in the pulse coupled connection network, and V L is the magnification factor of the link input. W ijkl is the interconnection factor, which is a 3×3 weight matrix linking the inputs, and refers to the connection distance between a neuron and its neighbors, and has W ijkl =1 / ((ik) 2 +(jl) 2 ).

[0059] Furthermore, the modulation field U ij (n) Considering F from the input field ij (n) and L ij (n) of the total internal activity, while the link input L ij The weight of (n) is β. β is the link coefficient that determines the weight of the link channel in the internal activity, and its value is given by Given, where std ij is the standard deviation of the spike rate values ​​of the 8 neighbors starting from the spike rate of (i, j). Here std ij Indicates the discreteness of the sample data and controls the β value. Overall modulation part U ij The output of (n) determines whether the neuron fires, U ij (n)>E ij E ij is the dynamic threshold for firing the neuron, which is partially adjusted by the pulse generator. And can be represented by the expected average value θ of the spike rate of the encoded image. The pulse generator sets U ij (n) is compared with the expected mean value θ and ij >E ij Then, the output Y ij (n) is set to 1 and this firing state is passed to the neighboring neurons. When the neighboring neurons have a similar U as the (i,j) neuron ij (n), they will also trigger due to the pulse coupling effect. Finally, the target image after segmentation processing is obtained, realizing the spike coding function in the human brain visual system, and thus the function of human visual perception. It should be emphasized that the highest frequency peak corresponds to the simultaneous application of ultraviolet rays with wavelengths of 365nm and 254nm, while the lowest frequency peak corresponds to dark conditions, that is, conditions without light.

[0060] See also Figure 4 , Figure 4The schematic diagram of the principle of the image processing method of this embodiment is shown, wherein the optical image information is collected and converted by the sensory neuron array, and then encoded by the spike information encoder to obtain count pulses; then segmented and processed by the pulse coupled neural network, and finally the segmented image can be output to obtain the identified target image.

[0061] In summary, an image processing method provided in this embodiment obtains image information and converts the image information into a transmittable image signal; then, the image signal is converted into a spike signal through an oscillating artificial neuron device; the spike signal is then encoded to obtain a counting pulse; the number of counting pulses is used to characterize the size of the spike; further, the counting pulse is input into a pulse coupled neural network for segmentation processing to obtain a segmented target image. The entire process of the method of this embodiment can directly, continuously and in real time respond to image information, and generate different spike signals and counting pulses according to different effective inputs, and finally achieve the output of the target image after segmentation processing, and realize the segmentation and segmented output of the photoelectric information, completing the spike coding function and visual perception function in the human brain visual system. The method of this embodiment can also promote the construction of artificial visual perception systems and pave the way for the development of bio-inspired photoelectric devices, light-driven robots and neuromorphic computing.

[0062] Second embodiment

[0063] See also Figure 5 Based on the same inventive concept, this embodiment provides an image processing device 300, the device 300 comprising:

[0064] An acquisition module 301 is used to acquire image information and convert the image information into a transmittable image signal;

[0065] A conversion module 302, configured to convert the image signal into a spike signal through an oscillating artificial neuron device;

[0066] The encoding module 303 is used to encode the peak signal to obtain a count pulse; wherein the count pulse is used to characterize the size of the peak;

[0067] The segmentation module 304 is used to input the counting pulses into a pulse coupled neural network for segmentation processing to obtain a segmented target image.

[0068] As an optional implementation manner, the encoding module 303 is specifically used to:

[0069] converting the spike signal into a periodic electrical signal;

[0070] The periodic electrical signal is converted into counting pulses.

[0071] As an optional implementation, the pulse coupled neural network includes: a first pulse coupled neural network and a second pulse coupled neural network; the segmentation module 304 is specifically used to:

[0072] Inputting the counting pulse into the first pulse coupled neural network for segmentation to obtain a feedback electrical signal and a link signal;

[0073] The feedback electrical signal and the link signal are input into the second pulse coupled neural network for processing to obtain a target image.

[0074] As an optional implementation, the second pulse coupled neural network is a simplified single-layer pulse coupled neural network of a two-dimensional local network.

[0075] As an optional implementation manner, the segmentation module 304 is further specifically configured to:

[0076] Based on U ij (n) = F ij (n)(1+βL ij (n))、E ij (n) = θ and Get the target image; where U ij (n) is the modulation field, F ij (n) is the feedback electrical signal, L ij (n) and link signal, β is the link signal weight, E ij is the dynamic threshold for triggering neurons, (i, j) is the coordinate of neurons, Y ij is the target image.

[0077] It should be noted that the specific implementation and technical effects of the device 300 provided in the embodiment of the present invention are the same as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference may be made to the corresponding contents in the aforementioned method embodiment.

[0078] If the functional module integrated in the device provided by the present invention is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the method of the above embodiment, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0079] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the description of the above specific languages ​​is for disclosing the best mode of the present invention.

[0080] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0081] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the intention that the claimed invention requires more features than those explicitly recited in each claim. More specifically, as reflected in the claims below, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present invention.

[0082] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0083] In addition, those skilled in the art will appreciate that, although some embodiments herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in the claims below, any one of the claimed embodiments may be used in any combination.

[0084] The various component embodiments of the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all functions of some or all components in a gateway, proxy server, or system according to an embodiment of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0085] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc., does not indicate any order. These words may be interpreted as names.

Claims

1. An image processing method, characterized in that: include: Acquiring image information and converting the image information into a transmittable image signal; Converting the image signal into a spike signal through an oscillating artificial neuron device; Encoding the peak signal to obtain counting pulses; wherein the number of the counting pulses is used to characterize the size of the peak; Inputting the counting pulses into a pulse coupled neural network for segmentation processing to obtain a segmented target image; The step of encoding the peak signal to obtain a counting pulse comprises: Convert the spike signal into a periodic electrical signal; convert the periodic electrical signal into a counting pulse; wherein the number of the counting pulses is used to represent the peak size of the spike signal, and a larger number corresponds to a larger peak.

2. The method according to claim 1, characterized in that The pulse coupled neural network comprises: a first pulse coupled neural network and a second pulse coupled neural network; the step of inputting the count pulses into the pulse coupled neural network for segmentation processing to obtain a segmented target image comprises: Inputting the counting pulse into the first pulse coupled neural network for segmentation to obtain a feedback electrical signal and a link signal; The feedback electrical signal and the link signal are input into the second pulse coupled neural network for processing to obtain a target image.

3. The method according to claim 2, characterized in that The second pulse coupled neural network is a simplified single-layer pulse coupled neural network of a two-dimensional local network.

4. The method according to claim 2, characterized in that: The step of inputting the feedback electrical signal and the link signal into the second pulse coupled neural network for processing to obtain a target image comprises: Based on U ij (n) = F ij (n)(1+βL ij (n))、E ij (n) = θ and Get the target image; where U ij (n) is the modulation field, F ij (n) is the feedback electrical signal, L ij (n) is the link signal, θ is the expected average of the spike rate of the encoded image, β is the link signal weight, E ij is the dynamic threshold for triggering neurons, (i, j) is the coordinate of neurons, Y ij is the target image.

5. An image processing device, characterized in that: include: An acquisition module, used for acquiring image information and converting the image information into a transmittable image signal; A conversion module, used for converting the image signal into a spike signal through an oscillating artificial neuron device; An encoding module, used for encoding the peak signal to obtain count pulses; wherein the number of the count pulses is used to characterize the size of the peak; The encoding module is specifically used for: Convert the spike signal into a periodic electrical signal; convert the periodic electrical signal into a counting pulse; wherein the number of the counting pulses is used to represent the peak size of the spike signal, and a larger number corresponds to a larger peak; The segmentation module is used to input the counting pulses into a pulse coupled neural network for segmentation processing to obtain a segmented target image.

6. The device according to claim 5, characterized in that The pulse coupled neural network comprises: a first pulse coupled neural network and a second pulse coupled neural network; the segmentation module is specifically used for: Inputting the counting pulse into the first pulse coupled neural network for segmentation to obtain a feedback electrical signal and a link signal; The feedback electrical signal and the link signal are input into the second pulse coupled neural network for processing to obtain a target image.

7. The device according to claim 6, characterized in that The second pulse coupled neural network is a simplified single-layer pulse coupled neural network of a two-dimensional local network.

8. The device according to claim 6, characterized in that The segmentation module is further specifically used for: Based on U ij (n) = F ij (n)(1+βL ij (n))、E ij (n) = θ and Obtaining a target image; Among them, U ij (n) is the modulation field, F ij (n) is the feedback electrical signal, L ij (n) is the link signal, θ is the expected average of the spike rate of the encoded image, β is the link signal weight, E ij is the dynamic threshold for triggering neurons, (i, j) is the coordinate of neurons, Y ij is the target image.

Images