Adaptive weighted guided image filtering for depth enhancement in shape-from-focus

The dual oil circuit centrifugal fuel nozzle is made of martensitic stainless steel, which has complex morphological characteristics. The surface roughness characteristics of the fuel nozzle directly affect the degree of fuel atomization and the spray cone angle. The surface characterization of the fuel nozzle is investigated by the fractal analysis method. A sequence of images of an unheated treatment fuel nozzle and a heated treatment fuel nozzle are captured by the super-depth digital camera. The 3-D point cloud of the fuel nozzle is acquired by the shape from focus technique, and its three-dimensional (3-D) fractal dimensions are calculated and analyzed by the 3-D sandbox counting method. The proposed method can characterize the surface morphology well, including the standard metal processing surface and the fuel nozzle surface, and the experiments show that the 3-D surface fractal dimension is positively correlated with the surface roughness parameter. The 3-D surface fractal dimensions of the unheated treatment fuel nozzle were 2.6281, 2.8697, and 2.7620, compared with the heated treatment fuel nozzles dimensions of 2.3021, 2.5322, and 2.3327. Thus, the 3-D surface fractal dimension value of the unheated treatment is larger than that of the heated treatment and is sensitive to surface defects. This study indicates that the 3-D sandbox counting fractal dimension method is an effective method to evaluate the fuel nozzle surface and other metal processing surfaces.

show abstract

“…The concept of SFF was first proposed by Nayar [ 18 ]. SFF techniques are usually performed in the following steps [ 19 ]. As shown in Figure 1 .…”

Section: 3d Point Cloud Extraction Principle Of the Fuel Nozzlementioning

confidence: 99%

Fractal Analysis of Fuel Nozzle Surface Morphology Based on the 3D-Sandbox Method

Hou

Chen

2023

Micromachines

View full text Add to dashboard Cite

show abstract

“…In the third step, the initial focus volume is improved and outputs an enhanced image focus volume. For this, a large number of linear and non-linear approaches are suggested in the literature [25]. Finally, a depth map is constructed by selecting the image frame from the sequence that exhibits the highest focus in the optical direction.…”

Section: Background 21 Shape From Focusmentioning

confidence: 99%

Enhancing Focus Volume through Perceptual Focus Factor in Shape-from-Focus

Ashfaq,

Mahmood

2023

Mathematics

View full text Add to dashboard Cite

Shape From Focus (SFF) reconstructs a scene’s shape using a series of images with varied focus settings. However, the effectiveness of SFF largely depends on the Focus Measure (FM) used, which is prone to noise-induced inaccuracies in focus values. To address these issues, we introduce a perception-influenced factor to refine the traditional Focus Volume (FV) derived from a traditional FM. Owing to the strong relationship between the Difference of Gaussians (DoG) and how the visual system perceives edges in a scene, we apply it to local areas of the image sequence by segmenting the image sequence into non-overlapping blocks. This process yields a new metric, the Perceptual Focus Factor (PFF), which we combine with the traditional FV to obtain an enhanced FV and, ultimately, an enhanced depth map. Intensive experiments are conducted by using fourteen synthetic and six real-world data sets. The performance of the proposed method is evaluated using quantitative measures, such as Root Mean Square Error (RMSE) and correlation. For fourteen synthetic data sets, the average RMSE measure of 6.88 and correction measure of 0.65 are obtained, which are improved through PFF from an RMSE of 7.44 and correlation of 0.56, respectively. Experimental results and comparative analysis demonstrate that the proposed approach outperforms the traditional state-of-the-art FMs in extracting depth maps.

show abstract

An Edge-Preserving Image Denoising Framework by Adaptive Thresholding-Based DWT and Modified Deep Structured Architecture

Thamanam

Manjunathachari

Prasad

2023

Neural Process Lett

View full text Add to dashboard Cite

Adaptive weighted guided image filtering for depth enhancement in shape-from-focus

Cited by 9 publications

References 26 publications

Fractal Analysis of Fuel Nozzle Surface Morphology Based on the 3D-Sandbox Method

Fractal Analysis of Fuel Nozzle Surface Morphology Based on the 3D-Sandbox Method

Enhancing Focus Volume through Perceptual Focus Factor in Shape-from-Focus

An Edge-Preserving Image Denoising Framework by Adaptive Thresholding-Based DWT and Modified Deep Structured Architecture

Contact Info

Product

Resources

About