Machine Graphics and Vision

An improved generative design approach based on graph grammar for pattern drawing

Yufeng Liu, Yangchen Zhou, Fan Yang, Song Li, Jun Wu — Fri, 19 Apr 2024 00:00:00 +0000

Generative design is used to efficiently generate design solutions with powerful computational methods. Generative design based on shape grammar is currently the most commonly used approach, but it is difficult for shape grammar to formally analyze the generated pattern. Graph grammar derived from one-dimensional character grammar is mainly used for generating and analyzing abstract models of visual languages. However, there is a significant gap between the generated node-edge graphs and the representation of shape appearance. To address these problems, we propose an improved generative design approach based on virtual-node based continuous Coordinate Graph Grammar (vcCGG). This approach defines a new type of grammatical rule named node transformation rules to convert nodes into shapes with node transformation applications. By combining node transformation applications and L-applications in vcCGG, we can generate a node-edge graph as the structure of the pattern through L-applications, and then draw the shape outline, next adjust the positions of these shapes, thus relating abstract structures and the physical layouts of visual languages. At the end of the paper, we provide an example application of this approach: generating an illustration from Emma Talbot using a combination of node transformation applications and L-applications.

An age-group ranking model for facial age estimation

Joseph D. Akinyemi, Olufade F. W. Onifade — Thu, 24 Oct 2024 00:00:00 +0000

Age prediction has become an important Computer Vision task. Although this task requires the age of an individual to be predicted from a given face, research has shown that it is more intuitive and easier for humans to decide which of two individuals is older than to decide how old an individual is. This work follows this intuition to aid the age prediction of a face by exploiting the age information available from other faces. It goes further to explore the statistical relationships between facial features within age groups to compute age-group ranks for a given face. The resulting age-group rank is low-dimensional and age-discriminatory, thus improving age prediction accuracy when fed into an age predictor. Experiments on publicly available facial ageing datasets (FGnet, PAL, and Adience) reveal the effectiveness of the proposed age-group ranking model when used with traditional Machine learning algorithms as well as Deep Learning algorithms. Cross-dataset validation, a method of training and testing on entirely different datasets, was also employed to further investigate the effectiveness of this method.

An attention-based deep network for plant disease classification

Asish Bera, Debotosh Bhattacharjee, Ondrej Krejcar — Tue, 12 Nov 2024 00:00:00 +0000

Plant disease classification using machine learning in a real agricultural field environment is a difficult task. Often, an automated plant disease diagnosis method might fail to capture and interpret discriminatory information due to small variations among leaf sub-categories. Yet, modern Convolutional Neural Networks (CNNs) have achieved decent success in discriminating various plant diseases using leave images. A few existing methods have applied additional pre-processing modules or sub-networks to tackle this challenge. Sometimes, the feature maps ignore partial information for holistic description by part-mining. A deep CNN that emphasizes integration of partial descriptiveness of leaf regions is proposed in this work. The efficacious attention mechanism is integrated with high-level feature map of a base CNN for enhancing feature representation. The proposed method focuses on important diseased areas in leaves, and employs an attention weighting scheme for utilizing useful neighborhood information. The proposed Attention-based network for Plant Disease Classification (APDC) method has achieved state-of-the-art performances on four public plant datasets containing visual/thermal images. The best top-1 accuracies attained by the proposed APDC are: PlantPathology 97.74%, PaddyCrop 99.62%, PaddyDoctor 99.65%, and PlantVillage 99.97%. These results justify the suitability of proposed method.