A memristor-based architecture combining memory and image processing

Zhou, Jing; Yang, Xuejun; Wu, Junjie; Zhu, Xuan; Fang, Xudong; Huang, Da

doi:10.1007/s11432-013-4887-5

Cited by 20 publications

(19 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…l(b), if memristor Q is reset to 0 before IMP operation, the circuit will implement NOT operation, that is, q=�p. Truth table of IMP operation With the similar circuit and analysis method, we found that with different stimulating voltages, the circuit could finish AND operation [10], as shown in Fig. 2(a).…”

Section: The Basic Logic Circuits With Memristorsmentioning

confidence: 99%

Image segmentation with threshold based on memristors

Zhou

Tang

et al. 2013

2013 IEEE 4th International Conference on Electronics Information and Emergency Communication

Self Cite

View full text Add to dashboard Cite

Memristor is a newfound circuit element that has the ability of both memory and computing, which brings new opportunity for the development of computer architecture. Image processing is a type of memory-access-intensive application, where large part of time is spent in reading and writing image data. Therefore, we consider using memristors' property of having the ability of both memory and computing to realize some basic image operations, thus avoiding or reducing memory access of image data. In this paper, we propose algorithms achieving image segmentation with threshold based on memristors. First of all, we consider 8-bit gray image segmentation with specific thresholds, including 64, 128 and 192, where the comparison step could by simple. Then, we focus on image segmentation with general threshold, where the key step is to implement comparison of two 8-bit data. We design the comparison algorithm for 8-bit data based on memristors and use it in image segmentation with general threshold. The experimental results and theoretical analysis indicate that, our design is right in function, and could reduce memory access effectively.

show abstract

Section: The Basic Logic Circuits With Memristorsmentioning

confidence: 99%

Image segmentation with threshold based on memristors

Zhou

Tang

et al. 2013

2013 IEEE 4th International Conference on Electronics Information and Emergency Communication

Self Cite

View full text Add to dashboard Cite

show abstract

“…window/neighborhood selection 9: DImg = |window − window(w r + 1, w r + 1)| difference/distance image 10: windowM ask = DImg ≤ η Variable Pixel G-Neighbors are those with value1 11: N Zcount = countN onZeros(windowM ask) counting G-Neighbors 12: F (r − w r , c − w r ) = sum(window. * windowM ask)/N Zcount pixel-to-pixel masking and output calculation 13: end for 14: end for 15: end function lying on the nonlinear and variable characteristics of the memristor [23,24].…”

Section: Neuromorphic Circuits Using Memristorsmentioning

confidence: 99%

Memristive system design for variable pixel G-neighbor denoising filter

Aliakhmet

Sadykova

Mathew³

et al. 2018

IFS

View full text Add to dashboard Cite

Image blurring artifact is the main challenge to any spatial, denoising filters. This artifact is contributed by the heterogeneous intensities within the given neighborhood or window of fixed size. Selection of most similar intensities (G-Neighbors) helps to adapt the window shape which is of edge-aware nature and subsequently reduce this blurring artifact. The paper presents a memristive circuit design to implement this variable pixel G-Neighbor filter. The memristive circuits exhibits parallel processing capabilities (near realtime) and neuromorphic architectures. The proposed design is demonstrated as simulations of both algorithm (MATLAB) and circuit (SPICE). Circuit design is evaluated for various parameters such as processing time, fabrication area used, and power consumption. Denoising performance is demonstrated using image quality metrics such as peak signal-tonoise ratio (PSNR), mean square error (MSE), and structural similarity index measure (SSIM). Combining adaptive filtering method with mean filter resulted in average improvement of MSE to about 65% reduction, increase of PSNR and SSIM to nearly 18% and 12% correspondingly.

show abstract

“…基于单个忆阻器用于图像存储的忆阻交叉阵列 [11,23] , 改进了交叉点上忆阻器结构. 将突触设计电路放置在交叉点上, 如图 5 所示，它包含 4×4 交叉阵列、电压转换器、行列开关选择器、读写控制杨玖等: 一种反向串联忆阻突触电路的设计及应用图 4 生物学动作电位对应的 STDP 学习函数 2) 读入灰度图像.…”

Section: 突触电路用于交叉阵列的结构及设计步骤unclassified