Pengenalan Logo Kendaraan Menggunakan Metode Local Binary Pattern dan Random Forest

The vehicle logo is one of the features that can be used to identify a vehicle. Even so, a lot of Intelligent Transport System which are developed nowadays has yet to use a vehicle logo recognition system as one of its vehicle identification tools. Hence there are still cases of traffic crimes that haven't been able to be examined by the system, such as cases of counterfeiting vehicle license plates. Vehicle logo recognition itself could be done by using various feature extraction and classification methods. This research project uses the Local Binary Pattern feature extraction method which is often used for many kinds of image recognition systems. Then, the classification method used is Random Forest which is known to be effective and accurate for various classification problems. The data used for this study were as many as 2000 vehicle logo images consisting of 5 brand classes, namely Honda, Kia, Mazda, Mitsubishi, and Toyota. The results of the tests carried out obtained the best accuracy value of 88.89% for the front view logo image dataset, 77.03% for the side view logo image dataset, and 83% for the dataset with both types of images.

Logo Shape and Color as Drivers of Change in Brand Evaluation and Recognition

The purpose of the present study was to test whether logo shape and color affect emotional and cognitive response to a new logo. In the explorative part of the study, the effect of the amount of each of the additive primary color on logo perception was examined. Research was done on a sample of 190 students whose ratings were used as logo description measures. Two independent variables used in the study were logo shape (abstract vs. concrete) and logo color (original color vs. greyscale). Results showed that greyscale logos and logos that are concrete were recognized more accurately while liking was not related to either independent variable. It was also observed that the amount of red color in logo is negatively (correlated/related), and blue and green color are positively related to both logo recognition and logo liking. Practitioners are advised to note that factors affecting consumers’ cognition and emotion are different. Scientists can extend findings on the effect of amount of individual colors in a logo. This is one of the first works of research that examined the effect of logo color on brand recognition and has approached studying color in this way of averaging amount of each of the additive primary colors. External validity of the research is enhanced by testing the younger generation in their natural habitat of mobile phone environment.

Do You See What I See? Effectiveness of 360-Degree vs. 2D Video Ads Using a Neuroscience Approach

This study compares cognitive and emotional responses to 360-degree vs. static (2D) videos in terms of visual attention, brand recognition, engagement of the prefrontal cortex, and emotions. Hypotheses are proposed based on the interactivity literature, cognitive overload, advertising response model and motivation, opportunity, and ability theoretical frameworks, and tested using neurophysiological tools: electroencephalography, eye-tracking, electrodermal activity, and facial coding. The results revealed that gaze view depends on ad content, visual attention paid being lower in 360-degree FMCG ads than in 2D ads. Brand logo recognition is lower in 360-degree ads than in 2D video ads. Overall, 360-degree ads for durable products increase positive emotions, which carries the risk of non-exposure to some of the ad content. In testing four ads for durable goods and fast-moving consumer goods (FMCG) this research explains the mechanism through which 360-degree video ads outperform standard versions.

Logo Detection Using Deep Learning with Pretrained CNN Models

Logo detection in images and videos is considered a key task for various applications, such as vehicle logo detection for traffic-monitoring systems, copyright infringement detection, and contextual content placement. The main contribution of this work is the application of emerging deep learning techniques to perform brand and logo recognition tasks through the use of multiple modern convolutional neural network models. In this work, pre-trained object detection models are utilized in order to enhance the performance of logo detection tasks when only a portion of labeled training images taken in truthful context is obtainable, evading wide manual classification costs. Superior logo detection results were obtained. In this study, the FlickrLogos-32 dataset was used, which is a common public dataset for logo detection and brand recognition from real-world product images. For model evaluation, the efficiency of creating the model and of its accuracy was considered.

Patch-CNN: Deep learning for logo detection and brand recognition

Automatic logo detection and recognition is significantly growing due to the increasing requirements of intelligent documents analysis and retrieval. The main problem to logo detection is intra-class variation, which is generated by the variation in image quality and degradation. The problem of misclassification also occurs while having tiny logo in large image with other objects. To address this problem, Patch-CNN is proposed for logo recognition which uses small patches of logos for training to solve the problem of misclassification. The classification is accomplished by dividing the logo images into small patches and threshold is applied to drop no logo area according to ground truth. The architectures of AlexNet and ResNet are also used for logo detection. We propose a segmentation free architecture for the logo detection and recognition. In literature, the concept of region proposal generation is used to solve logo detection, but these techniques suffer in case of tiny logos. Proposed CNN is especially designed for extracting the detailed features from logo patches. So far, the technique has attained accuracy equals to 0.9901 with acceptable training and testing loss on the dataset used in this work.