Healthy vs. Unhealthy Food Images: Image Classification of Twitter Images

Obesity is a modern public health problem. Social media images can capture eating behavior and the potential implications to health, but research for identifying the healthiness level of the food image is relatively under-explored. This study presents a deep learning architecture that transfers features from a 152 residual layer network (ResNet) for predicting the level of healthiness of food images that were built using images from the Google images search engine gathered in 2020. Features learned from the ResNet 152 were transferred to a second network to train on the dataset. The trained SoftMax layer was stacked on top of the layers transferred from ResNet 152 to build our deep learning model. We then evaluate the performance of the model using Twitter images in order to better understand the generalizability of the methods. The results show that the model is able to predict the images into their respective classes, including Definitively Healthy, Healthy, Unhealthy and Definitively Unhealthy at an F1-score of 78.8%. This finding shows promising results for classifying social media images by healthiness, which could contribute to maintaining a balanced diet at the individual level and also understanding general food consumption trends of the public.

Analyze the usage of urban greenways through social media images and computer vision

Urban greenway is an emerging form of urban landscape offering multifaceted benefits to public health, economy, and ecology. However, the usage and user experiences of greenways are often challenging to measure because it is costly to survey such large areas. Based on the online postings from Instagram in 2017, this paper used Computer Vision (CV) technology to analyze and compare how the general public uses two typical greenway parks, The High Line in New York City and the Atlanta Beltline in Atlanta. Face and object detection analysis were conducted to infer user composition, activities, and key experiences. We presented the temporal patterns of Instagram postings as well as the group gatherings, smiling, and representative objects detected from photos. Our results have shown high user engagement levels for both parks while teens are significantly underrepresented. The High Line had more group activities and was more active during weekdays than the Atlanta Beltline. Stronger sense of escape and physical activities can be found in Atlanta Beltline. In summary, social media images like Instagram can provide strong empirical evidence for urban greenway usage when combined with artificial intelligence technologies, which can support the future practice of landscape architecture and urban design.

Multifeature Contrast Enhancement Algorithm for Digital Media Images Based on the Diffusion Equation

This paper studies the processing of digital media images using a diffusion equation to increase the contrast of the image by stretching or extending the distribution of luminance data of the image to obtain clearer information of digital media images. In this paper, the image enhancement algorithm of nonlinear diffusion filtering is used to add a velocity term to the diffusion function using a coupled denoising model, which makes the diffusion of the original model smooth, and the interferogram is solved numerically with the help of numerical simulation to verify the denoising processing effect before and after the model correction. To meet the real-time applications in the field of video surveillance, this paper focuses on the optimization of the algorithm program, including software pipeline optimization, operation unit balancing, single instruction multiple data optimization, arithmetic operation optimization, and onchip storage optimization. These optimizations enable the nonlinear diffusion filter-based image enhancement algorithm to achieve high processing efficiency on the C674xDSP, with a processing speed of 25 posts per second for 640 × 480 size video images. Finally, the significance means a value of super pixel blocks is calculated in superpixel units, and the image is segmented into objects and backgrounds by combining with the Otsu threshold segmentation algorithm to mention the image. In this paper, the proposed algorithm experiments with several sets of Kor Kor resolution remote sensing images, respectively, and the Markov random field model and fully convolutional network (FCN) algorithm are used as the comparison algorithm. By comparing the experimental results qualitatively and quantitatively, it is shown that the algorithm in this paper has an obvious practical effect on contrast enhancement of digital media images and has certain practicality and superiority.

Interactional gestures as soccer celebrations

The article presents a variety of gesture types used as celebrations during or after soccer matches and explains the forms, meaning, reference and functions of the gestures as a semiotic phenomenon. The qualitative analysis of media images and comments on celebratory performances shows that pre-planned, creative celebrations, including trademarks or signatures, which have recently overshadowed spontaneous, conventionalized displays of affect, take the form of interactional gestures of different types: performatives, regulators, pointing, icons, metaphors, pantomime, emblems or signs, as well as the form of compositions of gestures, such as icons and pointing. During the match, gestures of all the above types serve to display affects and take on other new functions. Also, even gestures like regulators, identified in literature as conversational ones, are used without the accompanying speech. A disintegrated speech context for the interpretation of the meaning and reference of celebratory gestures is provided in after-match media discourse.

Analysis of the Uniqueness and Similarity of City Landscapes Based on Deep Style Learning

The city landscape is largely related to the design concept and aesthetics of planners. Influenced by globalization, planners and architects have borrowed from available designs, resulting in the “one city with a thousand faces” phenomenon. In order to create a unique urban landscape, they need to focus on local urban characteristics while learning new knowledge. Therefore, it is particularly important to explore the characteristics of cities’ landscapes. Previous researchers have studied them from different perspectives through social media data such as element types and feature maps. They only considered the content information of a image. However, social media images themselves have a “photographic cultural” character, which affects the city character. Therefore, we introduce this characteristic and propose a deep style learning for the city landscape method that can learn the global landscape features of cities from massive social media images encoded as vectors called city style features (CSFs). We find that CSFs can describe two landscape features: (1) intercity landscape features, which can quantitatively assess the similarity of intercity landscapes (we find that cities in close geographical proximity tend to have greater visual similarity to each other), and (2) intracity landscape features, which contain the inherent style characteristics of cities, and more fine-grained internal-city style characteristics can be obtained through cluster analysis. We validate the effectiveness of the above method on over four million Flickr social media images. The method proposed in this paper also provides a feasible approach for urban style analysis.