Inverse correlation filters of objects features with optimized regularization for image processing

Parallel hierarchical memory (PI memory) is a new type of memory that is designed to improve the performance of parallel computing systems. PI memory is composed of two blocks: a mask RAM and a tail element RAM. The mask RAM stores the masks that are used to encode the information, while the tail element RAM stores the actual information. The address block of the PI memory is responsible for generating the physical addresses of the cells where the tail elements and their masks are stored. The address block also stores the field of addresses where the array was written and associates this field of addresses with the corresponding external address used to write the array. The proposed address block structure is able to efficiently generate the physical addresses of the cells where the tail elements and their masks are stored. The address block is also able to store the field of addresses where the array was written and associate this field of addresses with the corresponding external address used to write the array. The proposed address block structure has been implemented in a prototype PI memory. The prototype PI memory has been shown to be able to achieve significant performance improvements over traditional memory architectures. The paper will present a detailed description of the PI transformation algorithm, a description of the different modes of addressing organization that can be used in PI memory, an analysis of the efficiency of parallel-hierarchical memory structures, and a discussion of the challenges and future research directions in the field of PI memory.

“…Comparing formulas (10) and (11), it can be seen that the PI memory with preliminary array transformation is more efficient compared to regular memory by the amount of 𝑟 − 𝐿.…”

Section: Research Resultsmentioning

confidence: 99%

Section: Analysis Of the Efficiency Of Parallelhierarchical Memory St...mentioning

confidence: 99%

“…Analyzing previous work [9,12,14] on parallel-hierarchical structures, we can identify the main disadvantages of these systems [8,10,15].…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Architektoniczne, Strukturalne I Funkcjonalne Cechy Równoległo-Hierarchicznej Organizacji Pamięci

Timchenko,

Kokriatska,

Tverdomed

et al. 2024

“…The considered properties of tensors motivate the investigation of the application of the tensor structure of image data in object recognition using correlation filters [7,11,19].…”

Section: Introductionmentioning

confidence: 99%

Tensor and Vector Approaches to Objects Recognition by Inverse Feature Filters

Kvуetnyy,

Bunyak,

Sofina

et al. 2024

Self Cite

The investigation of the extraction of image objects features by filters based on tensor and vector data presentation is considered. The tensor data is obtained as a sum of rank-one tensors, given by the tensor product of the vector of lexicographic representation of image fragments pixels with itself. The accumulated tensor is approximated by one rank tensor obtained using singular values decomposition. It has been shown that the main vector of the decomposition can be considered as the object feature vector. The vector data is obtained by accumulating analogous vectors of image fragments pixels. The accumulated vector is also considered as an object feature. The filter banks of a set of objects are obtained by regularized inversion of the matrices compiled by object features vectors. Optimized regularization of the inversion is used to expand the regions of object features capture with minimal error. The object fragments and corresponding feature vectors are selected through a training iterative process. The tensor and vector approaches create two channels for recognition. High efficiency of object recognition can be achieved by choosing the filter capture band and creating filter branches according to the given bands. The filters create a convolutional network to recognize a set of objects. It has been shown that the obtained filters have an advantage over known correlation filters when recognizing objects with small fragments.

Neurobiological Properties of the Structure of the Parallel-Hierarchical Network and Its Usage for Pattern Recognition

Timchenko,

Kokriatskaia,

Tverdomed

et al. 2024

The paper presents the analysis of neurobiological data on the existence of the structure of a parallel-hierarchical network. Discussed method of parallel-hierarchical transformation based on population coding and its application for the pattern recognition task. Based on the analysis, we can conclude that using the methods proposed, it is possible to measure the geometric parameters and properties of images, which can significantly increase the efficiency of processing, in particular estimating the center of mass based on moment characteristics. Experimental results demonstrate that due to various destabilizing factors, accurately measuring the energy center coordinates of laser beam spot images is challenging. However, training the PI network and classifying the fragments into "good" and "bad" can considerably enhance the accuracy of these measurements.