Some strategic sectors of the economy require that the raw material of their machines and equipment have mechanical properties that satisfy their use. Maraging steel is a material of great concern since it is necessary to have a high mechanical resistance associated with high fracture toughness. The traditional tests to determine the fracture toughness of this material before use in applications are the Charpy and KIC tests. However, this process is characterized by being exhaustive and requiring specialized and trained professionals. Thus, to reverse this situation, this work proposes a new approach to determine the mechanical properties of maraging steel. For this, initially, the method removes any artifacts present in the image resulting from the mode of acquisition. In sequence, this works tested the method Extended Minimum Transformation (EMT) and mathematical morphology to find these markers of the regions of the dimples. Then, the Adaptive Thresholding, Optimal Global Thresholdusing the Otsu Method and Watershed transformation methods were used to segment the dimples. In the end, the diameter of the dimples and the toughness of the material were calculated. Tests are carried out and compared with the result obtained by specialists using the traditional system to evaluate the proposed approach. The results obtained were satisfactory for the application because the proposed approach presented speed and precision to the conventional methods.

O Seam Carving é um método de redimensionamento capaz de modificar a largura ou altura de imagens sendo sensível ao seu conteúdo, esse algoritmo aplica uma função de energia para avaliar a importância de cada pixel. Em casos particulares, como imagens que contém pessoas, o método apresenta frequente deformação de objetos, devido a função de energia não ser apta a detecção de pessoa. Com isso em vista, este artigo apresenta uma formulação na função de energia para o Seam Carving específica para a preservação de pessoas nas imagens. Esta função de energia é elaborada a partir de uma rede neural que tem como argumentos de entrada a cor da pele para classificar o pixel em pele ou não pele.

Seam Carving is a content-aware image resizing method capable of modifying the width or height of pictures. Such an algorithm applies an energy function to evaluate the importance of each pixel in the image. In exceptional cases, such as images that contain people, the method frequently presents deformation of objects due to the energy function not being able to detect a person. In this context, this paper presents a modification of the energy function used in seam carving by employing a neural network which can detect human skin patterns. Such a modification aims at better-preserving people in images. The experiments show that the proposed method achieves superior performance in terms of visual quality through qualitative indexes compared to the original algorithm.