Multi-focus Imaging Sequences Research Articles

Three-dimensional reconstruction of wear particle surfaces using multi-focus image sequence

Wear particles hold morphological traits that are linked to wear rate and mechanisms. Wear particle analysis is vital in the context of wear monitoring. Current methods can be used in three-dimensional (3D) reconstruction for particle type recognition and wear mechanism identification. A 3D reconstruction method based on microscopic focusing and image processing is here proposed. A fixed-focus quasi-planar strategy is built using the defocusing principle. The stationary wavelet transform is employed to assess the degree of focus for the purpose of depth mapping, facilitating the construction of 3D particle models. The model is then optimized for surface morphology to address noise and unevenness. The reconstruction results of the proposed approach were compared with that of laser scanning confocal microscope with average errors of arithmetic mean height (Sa), root-mean-square height (Sq), and kurtosis (Sku) at 2.81%, 2.96%, and 10.06%, respectively. The algorithm is non-contact and adaptable, offering value across various fields.

Motionless shape-from-focus depth measurement via high-speed axial optical scanning

Shape-from-focus depth measurement is widely used in equipment manufacturing, biomedicine, heritage conservation, engineering measurement, etc. However, the acquisition of multi-focus image sequence is not very flexible and time-consuming in conventional shape from focus. Here, a novel depth measurement from shape from focus method based on ultrafast optical axial scanning was proposed. An electronically tunable lens was used to achieve high-speed focus shift, by synchronizing a CCD with the electronically tunable lens, multi-focus image sequence can be acquired at high speed (up to 2.5 ms). The focusing area of each multi-focus image was extracted by the energy of image gradient operator. Finally, the motionless depth measurement can be achieved. A tilted marker pen was used to test the performance of the depth measurement, the results show that the depth resolution of the proposed method is measured to be ∼3.2 cm in a depth range of ∼24 cm. The feasibility of the proposed method was verified using misplaced portrait sculptures. This method will further expand the application of depth measurement from shape from focus in human–computer interaction, 3D shape measurement, and augmented reality.

GIPC-GAN: an end-to-end gradient and intensity joint proportional constraint generative adversarial network for multi-focus image fusion

As for the problems of boundary blurring and information loss in the multi-focus image fusion method based on the generative decision maps, this paper proposes a new gradient-intensity joint proportional constraint generative adversarial network for multi-focus image fusion, with the name of GIPC-GAN. First, a set of labeled multi-focus image datasets using the deep region competition algorithm on a public dataset is constructed. It can train the network and generate fused images in an end-to-end manner, while avoiding boundary errors caused by artificially constructed decision maps. Second, the most meaningful information in the multi-focus image fusion task is defined as the target intensity and detail gradient, and a jointly constrained loss function based on intensity and gradient proportional maintenance is proposed. Constrained by a specific loss function to force the generated image to retain the information of target intensity, global texture and local texture of the source image as much as possible and maintain the structural consistency between the fused image and the source image. Third, we introduce GAN into the network, and establish an adversarial game between the generator and the discriminator, so that the intensity structure and texture gradient retained by the fused image are kept in a balance, and the detailed information of the fused image is further enhanced. Last but not least, experiments are conducted on two multi-focus public datasets and a multi-source multi-focus image sequence dataset and compared with other 7 state-of-the-art algorithms. The experimental results show that the images fused by the GIPC-GAN model are superior to other comparison algorithms in both subjective performance and objective measurement, and basically meet the requirements of real-time image fusion in terms of running efficiency and mode parameters quantity.

The Normalized Random Map of Gradient for Generating Multifocus Image Fusion

The multifocus image fusion is a kind of method in image processing to collecting the sharp information from multifocus image sequence. This method is purposed to simplify the reader understand the complex information of image sequence in an image only. There are many methods to generate fused image from several images so far. Many researchers have developed many new and sophisticated methods. They show complicated computation and algorithm. So, that it is difficult to understand by the new students or viewer. Furthermore, they get difficulties to create the new one. In order to handle this problem, the proposed method a concise algorithm which is able to generate an accurate fused image without using a complicated mathematical equation and tough algorithm. The proposed method is the normalized random map of gradient for generating multifocus image fusion. By generate random map of gradient, the algorithm is able to specify the coarse focus region accurately. The random map of gradient is a kind of information formed independently from independent matrix. This data has a significant role in predict the initial focus regions. The proposed algorithm successes to supersede difficulties of mathematical equations and algorithms. It successes to eliminate the mathematical and algorithm problems. Furthermore, the evaluation of proposed method based on the fused image quality. The Mutual Information and Structure Similarity Indexes become our key parameter assessment. The results show that the outputs have high indexes. It means it is acceptable. Then the implementation of multifocus image fusion will increase the quality of the applied fields such as remote sensing, robotics, medical diagnostics and so on. It is also possible implemented in other new fields.

基于多聚焦图像序列融合的筒状类工件内壁形貌重构方法

基于多聚焦图像序列融合的筒状类工件内壁形貌重构方法

Adaptive window iteration algorithm for enhancing 3D shape recovery from image focus

Depth from focus (DFF) is a technique for estimating the depth and three-dimensional (3D) shape of an object from a multi-focus image sequence. At present, focus evaluation algorithms based on DFF technology will always cause inaccuracies in deep map recovery from image focus. There are two main reasons behind this issue. The first is that the window size of the focus evaluation operator has been fixed. Therefore, for some pixels, enough neighbor information cannot be covered in a fixed window and is easily disturbed by noise, which results in distortion of the model. For other pixels, the fixed window is too large, which increases the computational burden. The second is the level of difficulty to get the full focus pixels, even though the focus evaluation calculation in the actual calculation process has been completed. In order to overcome these problems, an adaptive window iteration algorithm is proposed to enhance image focus for accurate depth estimation. This algorithm will automatically adjust the window size based on gray differences in a window that aims to solve the fixed window problem. Besides that, it will also iterate evaluation values to enhance the focus evaluation of each pixel. Comparative analysis of the evaluation indicators and model quality has shown the effectiveness of the proposed adaptive window iteration algorithm.

Three-dimensional surface microtopography recovery from a multifocus image sequence using an omnidirectional modified Laplacian operator with adaptive window size.

Optical microscopy enables the observation of highly magnified objects and material structures on microsurfaces, but it can only acquire 2D images. In order to observe areal features more accurately and intuitively, 3D surface microtopography recovery has been applied to form a 3D surface model of an object from its 2D image sequence. In the 3D reconstruction of the focus evaluation operator, we have the gray variance operator, the gray-scale difference absolute sum operator, the Roberts gradient operator, the Tenengrad gradient operator, the improved Laplace operator, etc. There are two problems with these operators: one is that there is no difference between (x,y) and the gray scale of the pixel in the diagonal direction in the field and the other is that the window size of the focus evaluation operator is fixed, e.g., 3×3, 5×5, etc. Thus, the size of the window for each pixel in the image is the same, and the small window may not cover enough field information while being vulnerable to noise. Large windows can cover more information, but they may result in a smoothing phenomenon, which affects the accuracy of the model. Different pixels around the field have different pixel colors when the size of the window is not the same. Therefore, this paper proposes a modified omnidirectional Laplacian operator with an adaptive window to automatically adjust the size of the window according to the color difference within the window. This also takes into consideration the pixels in the diagonal direction. In addition, very comprehensive verification experiments proved the conclusions.

All-in-focus image reconstruction under severe defocus.

Limited depth-of-focus is a problem in many fields of optics, e.g., microscopy and macro-photography. We propose a new physically based method with a space variant point spread function (PSF) to accomplish all-in-focus reconstruction (image fusion) from a multi-focus image sequence in order to extend the depth-of-field. The proposed method works well under strong defocus conditions for color image stacks of arbitrary length. Experimental results are provided to demonstrate that our method outperforms state-of-the-art image fusion algorithms for strong defocus on both synthetic as well as real data images.

Shape-From-Focus Depth Reconstruction With a Spatial Consistency Model

This paper presents a maximum a posteriori (MAP) framework to incorporate a spatial consistency prior model for depth reconstruction in the shape-from-focus (SFF) process. Existing SFF techniques, which reconstruct a dense 3-D depth from multifocus image frames, usually have poor performance over low-contrast regions and usually need a large number of frames to achieve satisfactory results. To overcome these problems, a new depth reconstruction process is proposed to estimate the depth values by solving an MAP estimation problem with the inclusion of a spatial consistency model. This consistency model assumes that within a local region, the depth value of each pixel can be roughly predicted by an affine transformation of the image features at that pixel. A local learning process is proposed to construct the consistency model directly from the multifocus image sequence. By adopting this model, the depth values can be inferred in a more robust way, especially over low-contrast regions. In addition, to improve the computational efficiency, a cell-based version of the MAP framework is proposed. Experimental results demonstrate the effective improvement in accuracy and robustness as compared with existing approaches over real and synthesized image data. In addition, experimental results also demonstrate that the proposed method can achieve quite impressive performance, even with only the use of a few image frames.

4-7 焦点ぼけ構造を介した光線空間の圧縮の検討(第4部門映像表現&立体映像技術)

4-7 焦点ぼけ構造を介した光線空間の圧縮の検討(第4部門映像表現&立体映像技術)

15-3 FPGAを用いた焦点ぼけ構造に基づく高品質な自由視点画像生成の検討(第15部門 自由視点映像関連技術)

15-3 FPGAを用いた焦点ぼけ構造に基づく高品質な自由視点画像生成の検討(第15部門 自由視点映像関連技術)

Automatic 3D reconstruction and visualization of microscopic objects from a monoscopic multifocus image sequence

Automatic 3D reconstruction and visualization of microscopic objects from a monoscopic multifocus image sequence