Detail práce
Detektor kožních onemocnění u technologie otisků prstů
Práce se zabývá problematikou detekce kožních onemocnění z poškozeného obrazu otisku prstu a implementace jejího řešení pomocí technik zpracování obrazu.
Zpracování obrazu, detekce objektů, kožní onemocnění, rozpoznání podle otisku prstu.
Studentka nejprve prezentovala výsledky, kterých dosáhla v rámci své práce. Komise se poté seznámila s hodnocením vedoucího a posudkem oponenta práce. Studentka následně odpověděla na otázky oponenta a na další otázky přítomných. Komise se na základě posudku oponenta, hodnocení vedoucího, přednesené prezentace a odpovědí studentky na položené otázky rozhodla práci hodnotit stupněm A.
Page 5: "There are two types of biometric systems: a verification system or an identification
system [19]. The purpose of the former is to authenticate a person's identity by comparing their sample to the one that was captured previously. The latter recognizes a person by going through the whole database to find a match."
There may be other types of biometric systems. Which type of system is described here? http://www.bbc.com/news/world-asia-china-39324431
The forensic science world is currently in turmoil over the question of "inversion of conditional probability". Let me give an example of an error of "inversion of conditional probability".
Because you are a student of Prof. M. Drahansky, the probability that you attend Brno Institute of Technology is 100%.
Therefore, because you attend Brno Institute of Technology, the probability that you are a student of Prof. M. Drahansky is 100%
The first statement (1) above is correct, but the second statement (2) is very incorrect. Most of the 24,000 people who attend Brno IT are not students of Prof. Drahansky (Perhaps 1 in 1,000= 0.1% are his students). Let's call "you attend Brno IT" the evidence. Let's call "you are a student of Prof. Drahansky" the hypothesis. We can say that the probability of the evidence is very high given the hypothesis, but the probability of the hypothesis given the evidence is very low.
Can you apply this concept to fingerprinting, using the hypothesis "these fingerprints come from the same person", and the evidence "the fingerprints are very similar"? This misunderstanding by forensic fingerprint examiners has caused identification mistakes to be made. A famous case in the U.S. is that of Brandon Mayfield - see https://oig.justice.gov/special/s0601/final.pdf
Češka Milan, doc. RNDr., Ph.D. (UITS FIT VUT), člen
Martínek Tomáš, doc. Ing., Ph.D. (UPSY FIT VUT), člen
Ryšavý Ondřej, doc. Ing., Ph.D. (UIFS FIT VUT), člen
Španěl Michal, Ing., Ph.D. (UPGM FIT VUT), člen
@bachelorsthesis{FITBT20057,
author = "\v{S}t\v{e}p\'{a}nka Barotov\'{a}",
type = "Bakal\'{a}\v{r}sk\'{a} pr\'{a}ce",
title = "Detektor ko\v{z}n\'{i}ch onemocn\v{e}n\'{i} u technologie otisk\r{u} prst\r{u}",
school = "Vysok\'{e} u\v{c}en\'{i} technick\'{e} v Brn\v{e}, Fakulta informa\v{c}n\'{i}ch technologi\'{i}",
year = 2017,
location = "Brno, CZ",
language = "czech",
url = "https://www.fit.vut.cz/study/thesis/20057/"
}