High performance and energy efficient sobel edge detection

Peng-o, Thaufig; Chaikan, Panyayot

doi:10.1016/j.micpro.2021.104368

Cited by 11 publications

(10 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Sobel edge technique is extensively utilized in the microscopic imaging, computer vision, and image processing 46 . The Sobel operator employs a gradient method to find an edge 47 .…”

Section: Methodsmentioning

confidence: 99%

“…The Sobel edge technique is extensively utilized in the microscopic imaging, computer vision, and image processing. 46 The Sobel operator employs a gradient method to find an edge. 47 The Sobel operator is a highly regarded technique for edge detecting, significantly outperformed than the Prewitt and Robert operators in terms of noise tolerance and ease of application.…”

Section: Image Processing Approachmentioning

confidence: 99%

See 1 more Smart Citation

Characterization of column flow regimes on horizontal tubes for falling‐film systems: An experimental approach

Kandukuri

Deshmukh

Katiresan

2022

Asia-Pacific J Chem Eng

View full text Add to dashboard Cite

The intertube flow regimes and hydrodynamic behavior of the liquid profile have a significant impact on the functioning of falling-film evaporators. Column flow is one of the fundamental flow modes, which is actively observed in many industrial evaporators. A high-speed digital photographic device is utilized to visualize the complete progression of column flow phases for intertube distances of 10/20/30/40 mm and Reynolds number (Re) values ranging from 41 to 583. The Sobel edge detection algorithm is implemented to quantify the flow parameters for each frame of a sequence. The research results indicated that the column flow regime between the inline horizontal tubes can be broadly classified into the following phases: columnar droplet flow, periodic column flow, satellite drops column flow, drift column flow, and mixing liquid film column flow. The findings show that the liquid jet diameters between the tubes range from 1.6 to 8.46 mm, an increase in the liquid jet diameter with Re and a decrease with tube-to-tube distance. The axial coverage of the liquid film profile beneath the tube differed from 2.07 to 3.99 mm and over the tube surface ranged from 1.14 to 2.68 mm. The formation of dry spots and flooding is a major problem in the operation of falling-film heat exchangers. The shape and size of the liquid jet have a direct impact on the interfacial area; understanding the entire progression of column flow regimes, as well as their characteristics, can help designers avoid the aforementioned problem.

show abstract

“…The Sobel edge technique is extensively utilized in the microscopic imaging, computer vision, and image processing 46 . The Sobel operator employs a gradient method to find an edge 47 .…”

Section: Methodsmentioning

confidence: 99%

Section: Image Processing Approachmentioning

confidence: 99%

Characterization of column flow regimes on horizontal tubes for falling‐film systems: An experimental approach

Kandukuri

Deshmukh

Katiresan

2022

Asia-Pacific J Chem Eng

View full text Add to dashboard Cite

show abstract

“…In literature, one might come across approaches that use gradient-based traditional methods [1][2][3] and machine learning-based studies that have recently become very popular [4][5][6][7][8][9]. Although machine learning-based approaches perform much better than traditional gradient-based methods, the high computational load induced by these methods is a serious concern that should be considered [10]. There are a variety of application areas of edge detection, such as machine vision [4,11], smart vehicle technologies [12][13][14], medical image processing [15][16], and security applications [17].…”

Section: Introductionmentioning

confidence: 99%

“…There are still efforts to improve edge detection in terms of efficiency and computational complexity. The recent trend of using machine learning in edge detection shows superior performance compared with classical gradient-based algorithms but creates a computation load [7,10,18]. Therefore, especially for hardware implementation, fast edge detection methods that do not require high processing power are still widely required, and new novel approaches are being proposed [19][20].…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, especially for hardware implementation, fast edge detection methods that do not require high processing power are still widely required, and new novel approaches are being proposed [19][20]. Peng-o et al [10] propose a light algorithm that improves processing speed and energy consumption by decreasing the number of arithmetic operations for Sobel edge detection. Xuan et al [19] have focused on the limitations of the traditional canny method.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Edge Detection Method Driven by Knowledge-Based Neighborhood Rules

Capkan

Altun

Fidan

2023

Int. j. eng. technol. innov.

View full text Add to dashboard Cite

Edge detection is a fundamental process, and therefore there are still demands to improve its efficiency and computational complexity. This study proposes a knowledge-based edge detection method to meet this requirement by introducing a set of knowledge-based rules. The methodology to derive the rules is based on the observed continuity properties and the neighborhood characteristics of the edge pixels, which are expressed as simple arithmetical operations to improve computational complexity. The results show that the method has an advantage over the gradient-based methods in terms of performance and computational load. It is appropriately four times faster than Canny method and shows superior performance compared to the gradient-based methods in general. Furthermore, the proposed method provides robustness to effectively identify edges at the corners. Due to its light computational requirement and inherent parallelization properties, the method would be also suitable for hardware implementation on field-programmable gate arrays (FPGA).

show abstract