厄瓜多尔中央大学的Stalyn Paucar及其同事开发了一种基于人工智能的Web应用程序，用于自动描述岩石薄片。该应用结合了计算机视觉和自然语言处理技术，通过分析岩石薄片图像生成文本和语音描述。研究人员构建了一个包含5600张图像和相应文本描述的数据集，用于训练混合深度学习模型。该模型在实验中表现出高准确性和BLEU评分，为地质学等领域提供了新的工具。该应用已部署为Web应用程序，供公众使用，并开源了代码。

🔍该研究的核心在于开发一个基于人工智能的Web应用程序，用于自动描述岩石薄片，该应用结合了计算机视觉和自然语言处理技术。

🖼️研究使用了一个包含5600张岩石薄片图像的数据集，这些图像被分为14个岩石类型，包括流纹岩、安山岩、玄武岩等，每种类型包含400张图像，其中200张在普通偏光下拍摄，200张在交叉偏光下拍摄。

💡该模型使用EfficientNetB7从图像中提取特征，并通过Transformer网络生成文本描述，然后使用语音合成服务将文本转换为语音。实验结果显示，该模型具有0.892的准确率和0.71的BLEU评分。

🌍该Web应用程序为研究、专业和学术应用提供了潜在的实用性，并已部署供公众使用。研究人员还开源了该应用的源代码，方便其他研究者使用和改进。

Open-source: Automatic description of rock thin sections: A web application. Delighted to share Stalyn Paucar and colleagues work from Ecuador (Universidad Central del Ecuador) published this week.

Abstract
The identification and characterization of rock types is a core activity in geology and related fields, including mining, petroleum, environmental science, industry, and construction. Traditionally, this task is performed by human specialists who analyze and describe the type, composition, texture, shape, and other properties of rock samples, whether collected in-situ or prepared in a laboratory. However, the process is subjective, dependent on the specialist’s experience, and time-consuming. This study proposes an artificial intelligence-based approach that combines computer vision and natural language processing to generate both textual and verbal descriptions from images of rock thin sections. A dataset of images and corresponding textual descriptions is used to train a hybrid deep learning model. Features extracted from the images using EfficientNetB7 are processed by a Transformer network to generate textual descriptions, which are then converted into speech using a speech synthesis service. The experimental results show an accuracy of 0.892 and a BLEU score of 0.71. This model offers potential utility for research, professional, and academic applications and has been deployed as a web application for public use.

“One of our main contributions is the creation of a dataset containing 5600 rock thin section images, organized into 14 rock type categories, along with textual descriptions. This dataset serves as a key resource for the supervised learning of the automatic description model and may also benefit other related research.”

“The dataset is organized into 14 rock categories: rhyolite, andesite, basalt, granite, diorite, gabbro, ultramafic rock, phyllite, schist, gneiss, marble, sandstone, limestone, and shale. Each category contains 400 images, with 200 in plain polarized light and 200 in cross-polarized light.”

https://www.sciencedirect.com/science/article/pii/S2666544125000140
GitHub: https://github.com/stalyn314/Thin_Section