隨著科技的進步與資訊科學的發展，大量的資訊處理自動化逐漸取代傳統人工技術，然而不恰當地使用自動化技術，卻可能危害人類的權益與空間。為避免過度濫用機器自動化對人類所造成的災害，本研究根據不同的適用情境，分別提出以靜態及動態圖型為基礎的人機區分方法，透過簡單的影像處理技術，產生機器難以分析但人類能夠易於判別的人機辨識影像。並且由認知的角度，設計實驗進一步探討人類視覺優勢以及接受度，作為影像產生時的標準。最後，提出人機區分技術與應用情境整合實作的方法，以觀實效。 / The idea of using a computer program to distinguish humans from machines, sometimes referred to as the “Reverse Turing Test”, has emerged only quite recently. The term CAPTCHA, which stands for “Completely Automated Public Turing Test to Tell Computers and Humans Apart", is defined as: “a program that can generate and grade tests that: □ Most human can pass but □ Current computer program can’t pass! “ In this thesis, a texture-image based approach is developed to encode text information in such a way that machine vision algorithms will experience significant difficulties while human can extract the embedded text effortlessly. Both static images and dynamic sequences will be explored. It is anticipated that the cost of storing, and subsequently decoding information from such visual patterns will be prohibitedly high, both in terms of time and space complexity. To validate the postulation, fundamental principles of the human cognitive process will be examined. Experiments will also be carried out to gather user feedback and investigate the limitations of human visual systems. Finally, several application scenarios that call for the integration of a CAPTCHA will be identified and discussed.

Thesis (M.S.)--Rochester Institute of Technology, 2008. / Typescript. Includes bibliographical references (leaves 77-88).

Thesis (M.S.)--West Virginia University, 2010. / Title from document title page. Document formatted into pages; contains viii, 80 p. : ill. Includes abstract. Includes bibliographical references (p. 78-80).

During the last decade, there has been an increase in the number of automated programs (bots) that perform tasks such as harvesting information or making posts on social media. CAPTCHA was developed as a defense against bots, but several common CAPTCHAs have usability issues and are difficult for users to solve. This project aims to determine if a non-visible user input-based CAPTCHA can help solve this problem. The CAPTCHA looks for patterns in the user input, that is, signs that the input is controlled by scripted logic. The CAPTCHA is evaluated by looking at how capable it is at identifying patterns, human mouse movements and bot-controlled mouse movements. Additionally, it is investigated if there exists a data sequence size at which the pattern recognition algorithm can most successfully detect patterns and avoid false negatives. The results showed that interval sizes 40-50 provide the best results. Using these sizes, the pattern recognition algorithm was able to fulfill the commonly accepted rates of at least a 99 % success rate and at most a 10 % false negative rate. This shows that the CAPTCHA is robust under the circumstances investigated.

This paper describes basic methods used for optical character recognition. It explains all procedures of recognition from adjustment of picture, processing, feature extracting to matching algorithms. It compares methods and algorithms for character recognition obtained graphically distorted or else modified image so-called „captcha“, used in present. Further it compares method based on invariant moments and neural network as final classifier and method based on correlation between normals and recognized characters.

Work deals with code detection from control image. The document presents relevant image processing techniques dealing with a noise reduction, thresholding, color models, object segmentation and OCR. This project examines advantages and disadvantages of two selected methods for object segmentation and introduces developed system for object segmentation. The developed system for object segmentation and classification is realized, evaluated and results are discussed in details.

Participatory sensing systems need to gather information from a largenumber of participants. However, the openness of the system is a doubleedgedsword: by allowing practically any user to join, the system can beabused by an attacker who introduces a large number of virtual devices.This work proposes a hardened registration process for participatory sensingto raise the bar: registrations are screened through a number of defensivemeasures, towards rejecting spurious registrations that do not correspondto actual devices. This deprives an adversary from a relatively easytake-over and, at the same time, allows a flexible and open registrationprocess. The defensive measures are incorporated in the participatorysensing application. / Deltagande avkännings system behöver samlas från ett stort antal aktörer.Systems öppenhet är dock en dubbelsidigt värd: Genom att låta alla praktiskaanvändare deltagit, kan system utnyttja en av angripare som introducera ett stortantal virtuella enheter. I det här arbetet föreslå en härda registreringsprocess fördeltagare att identifiera höjning av ribban: registrering screenas genom ett antaldefensiva åtgärders, för att avvisa falska registreringar som inte motsvara aktuellaenheter. Detta berövar en motståndare från en relativt lätt övertagande och gersamtidigt en flexibel och öppen registreringsprocess. De defensiva åtgärdernainförlivas i deltagande avkännings applikation.

Made available in DSpace on 2016-04-29T13:17:36Z (GMT). No. of bitstreams: 1 Nelson Novaes Neto.pdf: 2137731 bytes, checksum: 25a81aebe23bcbbf562d10e4ca33ea55 (MD5) Previous issue date: 2011-10-19 / The present research had as primary goals: 1) To present a proposal for experimental procedure involving the use of the Internet as a laboratory for analysis of human behavior. 2) To use an online chat environment in order to assess whether users behavior of switching between chat rooms in a chat service can be influenced by the introduction or removal of a stimulus (CAPTCHA). A total of 700 users participated in an experimental design (three phases) to verify whether the manipulation of the CAPTCHA stimulus in stages 2 and 3 would affect users behavior as they enter the chat rooms. Two measures were employed to measure behavioral changes: a) number of times each user entered a chat room; and b) amount of time daily spent in the chat rooms for each user. It was hypothesised that for a considerable number of users, the removal of the CAPTCHA would increase the chances of switching to another chat room because of the elimination of the nuisance of answering the test. The results indicated that the pattern of behavior of users who entered the chat rooms was influenced by the effect of the manipulation of the CAPTCHA variable. However, the results were not significant enough to confirm the hypothesis. The measures employed to assess behavior changes were shown to be statistically significant when the CAPTCHA variable was reintroduced (Phase 3) to the participants after a 15-day period without the presence of the independent variable (Phase 2). This effect has shown that the reintroduction of CAPTCHA to the chain of gaining access to the room has significantly affected the behavioral pattern of all users, as compared to the previous stages, indicating that the process of reintroducing VI had, in part, aversive properties. All the same, it is important to consider that it has not been possible to determine whether this effect was caused by the influence of the CAPTCHA stimulus or by the simple change of environment with the inclusion of another component and condition in the chain of gaining access to the room. Since more and more people are increasingly using the Internet, the study of this environment can make a strong contribution to the science of behavior analysis / A presente pesquisa pretendeu: 1) Apresentar uma proposta de procedimento experimental para utilizar a Internet como um laboratório para o estudo do comportamento. 2) Utilizar um ambiente de bate-papo online para avaliar se o comportamento de troca de sala por participantes em um serviço de bate-papo pode ser alterado pela apresentação ou remoção de um estímulo (CAPTCHA). Um total de 700 participantes foram submetidos a um delineamento experimental (três fases) para verificar se a manipulação do estímulo CAPTCHA nas Fases 2 e 3 estabeleceria algum efeito sobre o comportamento de entrar nas salas, avaliado por duas medidas: a) número de acesso às salas de cada participante (entrada em uma sala); e b) permanência em uma sala por dia de cada participante. A hipótese da pesquisa era a de que, para boa parte dos participantes, a remoção do CAPTCHA aumentaria a probabilidade de mudança de sala, pela eliminação do incômodo de responder ao teste. Os resultados indicaram que o padrão comportamental de entrar nas salas pelos participantes foi influenciado pelo efeito da manipulação da variável CAPTCHA. Porém, os resultados não foram significativos para comprovar a hipótese de que a remoção do CAPTCHA aumentaria a probabilidade de mudança de sala. As medidas para o comportamento de entrada, número de acesso às salas e tempo de permanência nelas sofreram mudanças estatisticamente significativas apenas quando a variável CAPTCHA foi reapresentada (Fase 3) aos participantes após um período de 15 dias sem a presença da variável independente (Fase 2). Este efeito demonstrou que a reintrodução do CAPTCHA na cadeia de acesso à sala afetou consideravelmente o padrão comportamental de todos os participantes, quando comparados às fases anteriores, demonstrando que o processo de reintrodução da VI apresentou, em parte, propriedades aversivas. Mesmo assim, é importante considerar que não foi possível decidir se este efeito foi devido à influência do estímulo CAPTCHA ou à simples mudança no ambiente com a inclusão de um componente e condição na cadeia de respostas para acesso à sala. A tendência para o uso desse tipo de ambiente cresce consideravelmente e, nas condições gerais, seu estudo pode oferecer uma grande contribuição para a ciência da análise do comportamento