Multi-focus image fusion for accurate measurement of nonwoven structures

Blue calico is a highly valued folk handicraft that forms part of China’s national intangible cultural heritage. Thus, blue calico is a worthy target for reconstruction using modern image processing technology. Extracting the visual components or elements of a blue calico pattern is one way to capture the underlying design and enable innovation in traditional patterns using modern techniques. This paper presents a method of element extraction and classification based on a smart convolutional neural network (CNN), with an improved CifarNet structure, which we call CalicoNet. Initially, the algorithm for element extraction is implemented to generate element samples of blue calico. This process includes gray scaling, binarization, and contour extraction. We construct a data set of elements with 12 types. Then, four critical hyper-parameters, the batch-size, dropout ratio, learning rate, and pooling strategy, are optimized by a comparative analysis. A combination classifier strategy is subsequently added to the fully connected layers to strengthen the feature expression in the corresponding classes. Finally, the superiority of the proposed CalicoNet is verified through a comparison with other sophisticated CNNs. Experimental results demonstrate that CalicoNet achieves a validation accuracy of 99.2% for the training set, a total time of 1.13 hours for the whole data set, and a test mean accuracy precision of 98.66%. The robust performance of the proposed method across the element data set indicates that CalicoNet is a promising approach for element extraction and classification.

Section: Related Workmentioning

confidence: 99%

Element extraction and convolutional neural network-based classification for blue calico

Jia

Liu

2020

“…They also proposed a RBI that selects some source points according to the maximum gradient matrix, forms fiber boundaries through source point diffusion and then performs image fusion. 29 Chen et al 3 proposed a new MFF algorithm based on NSST to measure the fiber diameter and orientation. In this study, the rule of a large absolute value was used to fuse the high-frequency sub-band, while the rule of large regional variance was used to fuse the low-frequency sub-band.…”

mentioning

confidence: 99%

mentioning

confidence: 99%

Spectral- and spatial-based multi-focus image fusion method towards multi-layer nonwovens

Zhu

Sun

et al. 2023

In the microscopic imaging scenario where the object thickness exceeds the depth of field of the microscope, multi-focus image fusion (MFF) is an effective method to generate an all-in-focus image. However, for nonwoven fabric for which the captured image number is up to 100 or more, the existing methods often underperform in areas near the fiber edges, owing to image ghosting and noise accumulation caused by the platform moving. To address the above problem, this paper presents a method designed to fuse multi-layer micro-images based on the combination of spectral and spatial features of the images. Firstly, the spectral domain-based map is generated by decomposition and reconstruction of the high-frequency and low-frequency components of the images, aimed at obtaining the edge information. Simultaneously, the spatial domain-based fuse map is built through sharpness measurement, referring to visual perception. Finally, the two methods are combined via an optimized weight to obtain an all-in-focus fused image. Four groups of real-world data consisting of 100 multi-focus nonwoven images are utilized to verify the superiority of this method. The experimental results demonstrate that the proposed method can obtain satisfactory performance in terms of both human visual evaluation and objective evaluation compared with the image fusion framework based on the convolutional neural network, MFF, region-based image fusion algorithm and convolutional neural network state-of-the-art fusion methods.

“…Therefore, measurements based on these incompletely focused images will be inaccurate and some errors would be generated during subsequent processing due to these defocusing phenomenon. 1 In this article a method of multi-focused image fusion is introduced, using fusion technology to merge two or more multi-focused images into a single image, which could be used to identify the full objects at a range of different focus depths. Through this fusing method, a final high-quality image with all the objects across different focus layer could be merged and visualized for further processing.…”

mentioning

confidence: 99%

A novel multi-focus image fusion method of nonwovens based on GHM multiwavelet transform technology

Chen

Deng

Xin

et al. 2018

In the digital optical microscope, the depth of field is limited in the image acquisition of nonwoven fabrics. The image of the fabric under the single focus image cannot achieve a uniform focus in the whole field of vision, which leads to the blurring of some regions. A new method of multi-focus image fusion based on the Geronimo-Hardin-Massopust (GHM) multiwavelet transform is introduced in this article, which realizes the digital image fusion of a sequence of images taken at different focus settings to achieve a clearer focus fusion of the fiber mesh showing the full field of view within a single image. In this article, a self-built nonwovens micro imaging system is used to collect the image sequence of the fabric at different focus images, and the initial image sequence is processed by critical sampling prefiltering. The high and low frequency components of the image are processed by different fusion rules, and the fusion image of the initial fabric is obtained through the fusion of multiwavelets and inverse transformation. Then, the fusion image of the initial fabric and the subsequent focus image are fused, using the above method, and all the fiber areas after the fusion can be clearly shown to end the operating. Experiments show that the fusion method can solve the difficulty of accurate focusing in a single image with full field of vision.