Brand style and product identity are critical to the core value of a brand. Yet how to identify the style and identity is highly dependent on the human expert’s judgment. As deep learning for image recognition has made a rapid process in recent years, it’s the application of brand style and design features have potential. This investigation assessed the car styling evolution of two car brands, Dodge and Jaguar, by training convolutional neural network. The method used heat map analysis of deep learning and was supplemented by statistical methods. The two datasets in this investigation were the car design features dataset and the car style images dataset. Results using the deep learning method show that the average accuracy of the last ten under verification modes was 95.90%, while 78% of the new cars continue the early brand style. Moreover, Jaguar had a higher proportion of style consistency than Dodge. Results using statistical methods reveal two cars had evolved in two different trends regarding the vehicle length. In terms of the design features, Jaguar had no noticeable design features of the rocket-tailfin. The heat map method of deep learning indicates a design feature’s focus area, and the method is beneficial for future brand style analysis.

This paper presents a new method of using a convolutional neural network (CNN) in machine learning to identify brand consistency by product appearance variation. In Experiment 1, we collected fifty mouse devices from the past thirty-five years from a renowned company to build a dataset consisting of product pictures with pre-defined design features of their appearance and functions. Results show that it is a challenge to distinguish periods for the subtle evolution of the mouse devices with such traditional methods as time series analysis and principal component analysis (PCA). In Experiment 2, we applied deep learning to predict the extent to which the product appearance variation of mouse devices of various brands. The investigation collected 6,042 images of mouse devices and divided them into the Early Stage and the Late Stage. Results show the highest accuracy of 81.4% with the CNN model, and the evaluation score of brand style consistency is 0.36, implying that the brand consistency score converted by the CNN accuracy rate is not always perfect in the real world. The relationship between product appearance variation, brand style consistency, and evaluation score is beneficial for predicting new product styles and future product style roadmaps. In addition, the CNN heat maps highlight the critical areas of design features of different styles, providing alternative clues related to the blurred boundary. The study provides insights into practical problems for designers, manufacturers, and marketers in product design. It not only contributes to the scientific understanding of design development, but also provides industry professionals with practical tools and methods to improve the design process and maintain brand consistency. Designers can use these techniques to find features that influence brand style. Then, capture these features as innovative design elements and maintain core brand values.

Machine learning can classify the image clarity of low-cost nailfold capillaroscopy (NC) and can be applied to the design verification for other medical devices. The method can be beneficial for systems that require a large number of image datasets. This investigation covers the design, integration, image sharpness estimation, and deconvolution sharpening of the NC. The study applies this device to record two videos and extract 600 photos, including blurry and sharp images. It then uses the Laplace operator method for blur detection of the pictures. Statistics are recorded for each image’s Laplace score and the distribution of clear photos in NC. In this investigation, an algorithm called t-distributed stochastic neighbor embedding (t-SNE) is introduced into the NC image sharpness estimation issue. The t-SNE is employed as a data visualization tool to determine the cluster distribution of sharp images. The result shows the t-SNE method to classify sharp images of NC is close to the method combine statistic and Laplace operator for sharp image distribution. And the image captured from the low-cost NC that applying deconvolution can sharpen the image. It shows that the NC equipment combines with low-cost hardware and software computing advantages has broader, powerful, and complex applications. For long-term purposes, it is conducive for detecting people who have Raynaud’s phenomenon in rural areas of developing countries to realize the vision of health equity.