Hexagonal Image Processing for Computer Vision With Hexnet: A Hexagonal Image Processing Data Set and Generator

被引：0
作者：
Schlosser, Tobias [1 ]
Friedrich, Michael [1 ]
Meyer, Trixy [1 ]
Eibl, Maximilian [1 ]
Kowerko, Danny [1 ]
机构：
[1] Tech Univ Chemnitz, Fac Comp Sci, D-09107 Chemnitz, Germany
来源：
IEEE ACCESS | 2024年 / 12卷
关键词：
Image processing; Generators; Image synthesis; Lattices; Interpolation; Telescopes; Symbols; Solid modeling; Shape; Retina; Data set generation; hexagonal image processing; hexagonal lattice; hexagonal sampling; image generation; ATMOSPHERIC CHERENKOV TELESCOPES; NEURAL-NETWORKS; FRAMEWORK; RECONSTRUCTION; SIMULATION; RETINA;
D O I：
10.1109/ACCESS.2024.3510656
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
In the domains of image processing and computer vision, the exploration of hexagonal image processing systems has emerged as a fundamentally innovative yet nascent methodology that is motivated by the occurrence of hexagonal structures in the human visual perception system and nature itself. However, despite the possible benefits of hexagonal over conventional square approaches for image processing systems-which commonly utilize square pixels-no known publicly available hexagonal image data sets exist that would enable the evaluation of hexagonal approaches that have been developed within image processing and computer vision for tasks such as object detection and classification. For this purpose, this contribution proposes a foundation for hexagonal image data sets and their development: The Hexnet Hexagonal Image Processing Data Set (short Hexnet Dataset), which is based on The Hexagonal Image Processing Framework Hexnet (Hexnet Framework). As a baseline, three data subsets are introduced: 1) geometric primitives for the evaluation of hexagonal structures; 2) astronomical image processing, in which the descriptions of sensory elements of hexagonal telescope arrays have been leveraged for the detection and classification of synthesized atmospheric events; and 3) conventional image data sets, which provides hexagonally transformed versions of commonly evaluated square imagery.
引用
收藏
页码：189884 / 189901
页数：18
相关论文
共 86 条
  • [11] Zaidi S.S.A., Ansari M.S., Aslam A., Kanwal N., Asghar M., Lee B., A survey of modern deep learning based object detection models, Digit. Signal Process., 126, (2022)
  • [12] Rosenblatt F., The Perceptron-A Perceiving and Recognizing Automaton, (1957)
  • [13] Rosenblatt F., The perceptron: A probabilistic model for information storage and organization in the brain, Psychol. Rev., 65, 6, pp. 386-408, (1958)
  • [14] Manning T., Sleator R.D., Walsh P., Biologically inspired intelligent decision making: A commentary on the use of artificial neural networks in bioinformatics, Bioengineered, 5, 2, pp. 80-95, (2014)
  • [15] Staunton R.C., Storey N., A comparison between square and hexagonal sampling methods for pipeline image processing, Proc. SPIE, 1194, (1990)
  • [16] He X., Jia W., Hexagonal structure for intelligent vision, Proc. Int. Conf. Inf. Commun. Technol., pp. 52-64, (2005)
  • [17] He X., Hintz T., Wu Q., Wang H., Jia W., A new simulation of spiral architecture, Proc. Int. Conf. Image Process., Comput. Vis., Pattern Recognit., 2, pp. 570-575, (2006)
  • [18] Schlosser T., Manthey R., Ritter M., Entwurf und implementierung von Optimierungs-und funktionserweiterungen der hexagonalen bildrasterung in der videokompressionssoftware x264HMod, Proc. Studierendensymposium Informatik der TU Chemnitz, pp. 63-74, (2016)
  • [19] Curcio C.A., Sloan K.R., Packer O., Hendrickson A.E., Kalina R.E., Distribution of cones in human and monkey retina: Individual variability and radial asymmetry, Science, 236, 4801, pp. 579-582, (1987)
  • [20] Middleton L., Sivaswamy J., Hexagonal Image Processing: A Practical Approach, (2005)
123456789