•We propose to use a real time object detection methodology for the first time in the field of phishing web page/e-mail detection.•We released a bounding box annotated and a publicly available ...dataset which will hopefully be useful for further research.•The suggested model utilizes the web page/e-mail snapshots as the only source of information.•The proposed approach is invariant to underlying HTML source code and the language of the web page/e-mail.•The developed scheme shows competitive performance to the state of art deep learning based solutions.
With the advent of Internet and opportunities in e-commerce, a visual perception oriented cyber-attack so-called phishing has become one of the tremendous problems of the cyber world since it aims to access user credentials in order to gain illegal financial profit and steal sensitive personal data. In order to fight with this security threat, various studies using a different source of information such as URL, text content, DOM trees or visual features belonging to web pages have been utilized. Apart from other works, we propose a companion scheme to recognize brands of “zero hour” phishing web pages by localizing and classifying the target brand logos involved in page screenshots by solely use of computer vision methods in object detection manner. For this purpose, the features of Histogram of Oriented Gradients (HOG) have been employed to obtain visual representations of target brand logos in scale invariant fashion. In addition, throughout the classification, a max-margin loss equipped SVM classifier has been used in order to work with a low number of training images and to decrease the number of false positives. Moreover, we prepared a publicly available dataset having a total of 3060 training and 1979 unique phishing and legitimate web page/e-mail snapshots along with their bounding box annotations for evaluation and further academic usage. Detailed experiments show that, at the best configuration, our schema named “LogoSENSE” is able to achieve 93.50% precision and of 77.94% recall score along with obtaining F1 score of 85.02%. The experiments show that the proposed approach outperforms SIFT based detection and presents comparative results against a state-of-art deep learning based object detection method. As a result, LogoSENSE serves promising results in terms of detection accuracy and run-time efficiency, yielding a companion tool that can be used as a brand recognition mechanism for phishing web pages and emails.
Purpose
The purposes of two experiments were to examine how brands may create a broad brand impression and benefit brand extensions by crafting logo frames.
Design/methodology/approach
Two ...experimental studies were conducted. Study 1 examines how removing and breaking logo frames expands perceived brand breadth. Study 2 considers the implication of this logo frame effect and indicates the impact of logo frames on brand extension scenarios.
Findings
Removing and breaking logo frames could expand perceived brand breadth and, in turn, benefits the brand extensions, especially for promotion-focused consumers. However, prevention-focused people held favorable brand extension attitudes when the brand logo constructs a complete frame due to its perceived trustworthiness.
Research limitations/implications
As an initial exploration, this study conceptualizes and manipulates logo frames as full framed, partial framed and open logo. Future research studies could include further design features in the examination.
Practical implications
If a brand seeks to be broad, removing or breaking its logo frame is an alternative. However, consequential negative impressions on brand extension attitudes among prevention-focused customers should be considered.
Originality/value
This study is the first investigation into the impacts of logo frame patterns on consumers’ perception of brand breadth and the consequent extension attitudes.
We contribute, through this paper, to the design of a novel variational framework able to match and recognize multiple instances of multiple reference logos in image archives. Reference logos and ...test images are seen as constellations of local features (interest points, regions, etc.) and matched by minimizing an energy function mixing: 1) a fidelity term that measures the quality of feature matching, 2) a neighborhood criterion that captures feature co-occurrence/geometry, and 3) a regularization term that controls the smoothness of the matching solution. We also introduce a detection/recognition procedure and study its theoretical consistency. Finally, we show the validity of our method through extensive experiments on the challenging MICC-Logos dataset. Our method overtakes, by 20%, baseline as well as state-of-the-art matching/recognition procedures.
Logo classification systems have become increasingly important in various industries for tasks, such as infringement detection and industrial production. However, challenges still exist in logo ...classification due to real-world image background interference, the high similarity between classes, labeling difficulties, and the insufficient representation of occlusion in single-view logos. Many existing algorithms fail to consider the data characteristics and the intrinsic information of multiple views, which limits their performance. To overcome these limitations, we developed a novel Cross-View Information Awareness Network (CVIA-Net) for logo classification. To differentiate between similar logo categories, the CVIA-Net novel learns context-shared features of the same category via a self-supervised way without labeled, which solves the problem of insufficient features due to occlusion. For single-view images, CVIA-Net establishes a "bottleneck" representation to address background interference. Extensive experiments on three datasets demonstrate that it outperforms state-of-the-art methods. The method is expected to advance the development of cross-view representation learning.
Deep learning for logo recognition Bianco, Simone; Buzzelli, Marco; Mazzini, Davide ...
Neurocomputing (Amsterdam),
07/2017, Letnik:
245
Journal Article
Recenzirano
Odprti dostop
In this paper we propose a method for logo recognition using deep learning. Our recognition pipeline is composed of a logo region proposal followed by a Convolutional Neural Network (CNN) ...specifically trained for logo classification, even if they are not precisely localized. Experiments are carried out on the FlickrLogos-32 database, and we evaluate the effect on recognition performance of synthetic versus real data augmentation, and image pre-processing. Moreover, we systematically investigate the benefits of different training choices such as class-balancing, sample-weighting and explicit modeling the background class (i.e. no-logo regions). Experimental results confirm the feasibility of the proposed method, that outperforms the methods in the state of the art.
Visual cues are pervasive on crowdfunding platforms. However, whether and how low validity visual cues can impact the behavior of backers remains largely unknown. In this article, we propose a ...disfluency-based heuristic framework for understanding the influence of low validity visual cues on equity crowdfunding platforms. Drawing on processing fluency theory and visual heuristics, we propose that backers often automatically process visual cues, and that the subjective experience of ease/difficulty with which backers perceptually process low validity visual cues serves as a heuristic and informs their perceptions of early-stage entrepreneurial ventures. We test our propositions focusing on logos (low validity visual cues that are particularly salient and ubiquitous on equity crowdfunding platforms) and logo complexity (a fundamental characteristic of logo design and established antecedent of processing disfluency). We contend that logo complexity can be interpreted by backers as a signal of venture innovativeness because more (vs. less) complex logos are more difficult to process, and thus, feel less familiar and more unique, original, and novel to backers. Since backers often value innovativeness, we further contend that logo complexity can positively impact backers' funding decisions. We find support for our framework and propositions using a multimethod approach comprising three studies: one survey, one field study, and one experiment. Theoretical contributions and managerial implications are also discussed.
•Logo complexity can inform backers' perceptions of venture innovativeness.•Increasing logo complexity can increase the amount of funds invested in ventures.•Visual cues can impact backers' perceptions and funding decisions.•Backers use the ease/difficulty with which they process visual cues as a heuristic.
Programski jezik Logo jedan je od prvih programskih jezika za poučavanje djece nastao još 1966., a primarno je služio za učenje geometrije. Logo se temelji na ideji kornjačine grafike, koja je i ...danas još uvijek itekako prisutna u razvijanju računalnog razmišljanja i za početno učenje programiranja. Jasno je da je u vrijeme nastajanja Loga ideja osobnog računala bila tek ideja iz znanstvene fantastike, pa i samog računarstva kao samostalne znanstvene discipline. Unatoč tome, vizionarski pogled Seymoura Paperta postavio je temelje računalnog razmišljanja i poučavanja programiranja od najranije dobi koji su danas sveprisutni. Kako je Papert bio primarno matematičar, s predmetom zanimanja za poučavanje matematike, tako je Logo zapravo nastao u svrhu poučavanje geometrije i olakšavanja djeci savladavanja osnovnih pojmova iz područja geometrije kao što su mnogokuti. Ipak, nema puno istraživanja koja se bave istraživanjem utjecaja Loga na razumijevanje osnovnih pojmova geometrije. Cilj ovog rada je istražiti utjecaj korištenja programskog jezika Logo u poučavanju geometrije koja se obrađuje u osmim razredima osnovne škole, s naglaskom na osnovne pojmove o mnogokutima, identificirati učestale pogreške pri učenju mnogokuta te ocijeniti učinkovitost Logo programa u poticanju interaktivnog učenja geometrije. U ovom istraživanju koristile su se kvalitativne i kvantitativne metode kako bi se pružio sveobuhvatan uvid u ovu temu. Istraživanje je pokazalo da primjena kornjačine grafike u programskom jeziku Logo u poučavanju osnovnih pojmova o mnogokutima rezultira boljim razumijevanjem pojmova mnogokuta kod učenika te potiče interaktivno učenje geometrije.
Abstract
With the advancement of the information society and the development of China’s economy, enterprises to digital, information, intelligent production requirements continue to improve, the ...application of industrial software gradually popularized in the production of enterprises. However, in the Internet era, the research on man-machine interface design is in full rage, but the man-machine interface design of domestic industrial software has not been paid attention to. The level of industrial software interface is seriously backward, disjointed with The Times, and completely contrary to, high technology, high efficiency and other industrial execution concepts. On the one hand, this phenomenon will affect the working efficiency of the staff in the operation of the software and the user experience, reduce manufacturing enterprises related to attract talent, on the other hand can also lead to the software under the same technical level, domestic industry software products to attract customers’ ability is insufficient, in the competition with foreign brand products in bad situation.
This research predicts that luxury versus non-luxury self-display enhances status and produces advantages in human social interactions. Across three experiments, findings support the following ...conclusions. First, luxury versus non-luxury brand logos associate positively with displayer wealth and status. Second, people wearing clothes with luxury brand logos receive preferential treatment over those not wearing luxury brand logos. Third, a person wearing a luxury brand logo while soliciting charitable donations receives larger contributions than a person not wearing a luxury brand logo. Fourth, cross-gender contexts are more effective than same-gender contexts for requester and target in influencing consumer donation behavior. Conclusion: luxury self-display may increase deference and compliance in presentations-of-self because conspicuous displays of luxury qualify as a costly signaling trait that elicits status-dependent favorable treatment in human social interactions.