Kang Dong Hee, Kim Na Kyong, Lee Wonoh, Kang Hyun Wook
Department of Mechanical Engineering, Chonnam National University, 77 Youngbong-ro, Buk-Gu, Gwangju, 61186, Republic of Korea.
Department of Industrial and Systems Engineering, Texas A&M University, College station, TX, 77843, United States.
Heliyon. 2024 Jul 27;10(15):e35358. doi: 10.1016/j.heliyon.2024.e35358. eCollection 2024 Aug 15.
As a technique in artificial intelligence, a convolution neural network model has been utilized to extract average surface roughness from the geometric characteristics of a membrane image featuring micro- and nanostructures. For surface roughness measurement, e.g. atomic force microscopy and optical profiler, the previous methods have been performed to analyze a porous membrane surface on an interest of region with a few micrometers of the restricted area according to the depth resolution. However, an image from the scanning electron microscope, combined with the feature extraction process, provides clarity on surface roughness for multiple areas with various depth resolutions. Through image preprocessing, the geometric pattern is elucidated by amplifying the disparity in pixel intensity values between the bright and dark regions of the image. The geometric pattern of the binary image and magnitude spectrum confirmed the classification of the surface roughness of images in a categorical scatter plot. A group of cropped images from an original image is used to predict the logarithmic average surface roughness values. The model predicted 4.80 % MAPE for the test dataset. The method of extracting geometric patterns through a feature map-based CNN, combined with a statistical approach, suggests an indirect surface measurement. The process is achieved through a bundle of predicted output data, which helps reduce the randomness error of the structural characteristics. A novel feature extraction approach of CNN with statistical analysis is a valuable method for revealing hidden physical characteristics in surface geometries from irregular pixel patterns in an array of images.
作为人工智能中的一种技术，卷积神经网络模型已被用于从具有微米和纳米结构的膜图像的几何特征中提取平均表面粗糙度。对于表面粗糙度测量，例如原子力显微镜和光学轮廓仪，以前的方法是根据深度分辨率在几微米的受限区域内对感兴趣区域的多孔膜表面进行分析。然而，结合特征提取过程的扫描电子显微镜图像，能为具有不同深度分辨率的多个区域提供表面粗糙度的清晰信息。通过图像预处理，放大图像明暗区域之间像素强度值的差异，从而阐明几何图案。二值图像的几何图案和幅度谱在分类散点图中证实了图像表面粗糙度的分类。从原始图像中裁剪出的一组图像用于预测对数平均表面粗糙度值。该模型对测试数据集的预测平均绝对百分比误差（MAPE）为4.80%。通过基于特征图的卷积神经网络结合统计方法提取几何图案的方法，提出了一种间接表面测量方法。该过程通过一组预测输出数据实现，有助于减少结构特征的随机误差。一种结合统计分析的卷积神经网络新型特征提取方法，是从图像阵列中不规则像素模式揭示表面几何中隐藏物理特征的有价值方法。
