The present article proposes a geometry-based fuzzy relational technique for capturing gradual change in human emotion over time available from relevant face image sequences. As associated features, we make use of fuzzy membership arising out of five triangle signatures such as - (i) Fuzzy Isosceles Triangle Signature (FIS), (ii) Fuzzy Right Triangle Signature (FRS), (iii) Fuzzy Right Isosceles Triangle Signature (FIRS), (iv) Fuzzy Equilateral Triangle Signature (FES), and (v) Other Fuzzy Triangles Signature (OFS) to achieve the task of appropriate classification of facial transition from neutrality to one among the six expressions viz. anger (AN), disgust (DI), fear (FE), happiness (HA), sadness (SA) and surprise (SU). The effectiveness of the Multilayer Perceptron (MLP) classifier is tested and validated through 10 fold cross-validation method on three benchmark image sequence datasets namely Extended Cohn-Kanade (CK+), M&M Initiative (MMI), and Multimedia Understanding Group (MUG). Experimental outcomes are found to have achieved accuracy to the tune of 98.47%, 93.56%, and 99.25% on CK+, MMI, and MUG respectively vindicating the effectiveness by exhibiting the superiority of our proposed technique in comparison to other state-of-the-art methods in this regard.

本文提出了一种基于几何的模糊关系技术，用于从相关面部图像序列中捕捉人类情绪随时间的逐渐变化。作为相关特征，我们利用由五个三角形签名产生的模糊隶属度，例如 - (i) 模糊等腰三角形签名 (FIS)，(ii) 模糊直角三角形签名 (FRS)，(iii) 模糊右等腰三角形签名 ( FIRS)、(iv) 模糊等边三角形签名 (FES) 和 (v) 其他模糊三角形签名 (OFS) 以实现面部从中性到六种表情之一的适当分类的任务，即。愤怒（AN）、厌恶（DI）、恐惧（FE）、快乐（HA）、悲伤（SA）和惊讶（SU）。多层感知器 (MLP) 分类器的有效性通过 10 折交叉验证方法在三个基准图像序列数据集上进行测试和验证，即扩展 Cohn-Kanade (CK+)、M&M Initiative (MMI) 和多媒体理解组 (MUG)。发现实验结果在 CK+、MMI 和 MUG 上分别达到了 98.47%、93.56% 和 99.25% 的准确率，通过展示我们提出的技术与其他最新技术相比的优越性，证明了有效性。这方面的艺术方法。