Presentasi sedang didownload. Silahkan tunggu

Presentasi sedang didownload. Silahkan tunggu

Program Studi S-1 Teknik Informatika FMIPA Universitas Padjadjaran

Presentasi serupa


Presentasi berjudul: "Program Studi S-1 Teknik Informatika FMIPA Universitas Padjadjaran"— Transcript presentasi:

1 Program Studi S-1 Teknik Informatika FMIPA Universitas Padjadjaran
COMPUTER VISION D10K-7C02 CV08: Binary Image Analysis: Moments and CCL Dr. Setiawan Hadi, M.Sc.CS. Program Studi S-1 Teknik Informatika FMIPA Universitas Padjadjaran

2 Citra Biner Citra yang hanya mengandung 2 macam intensitas, umumnya HITAM (0) atau PUTIH (1 atau 255) Merepresentasikan Background (0) dan Objek (1) Metode Pembuatan Preprocessing: Konversi Warna ke Gray Level Thresholding: Simple Thresholding Multilevel/Adaptive Thresholding OTSU Thresholding

3 Representasi Citra Biner

4 Histogram Citra Biner

5 Metode Pembuatan Citra Biner
Simple Thresholding

6 Metode Pembuatan Citra Biner
Multilevel/Adaptive Thresholding

7 Metode Pembuatan Citra Biner
OTSU Thresholding Nobuyuki Otsu, A Threshold Selection Method from Gray-Level Histograms, IEEE Transactions on System, Man, and Cybernetics. SMC-9(1), 1979, Electro-Technical Laboratory, Tokyo University(2007), Tokyo, Japan

8 Analisis Citra Biner Image Enhancement Image Analysis
Filter Morfologis (Preprocessing) Image Analysis Metode Moments Connected Component Labelling

9 MOMENTS

10 Moment Digunakan untuk mendapatkan properti geometris dari objek :
Ukuran (size) Posisi (pusat objek) Orientasi (kemiringan) Formula Moment

11 Coba cari nilai moment ini !
Momen Ordo 0 Untuk Mencari Luas Objek Coba cari nilai moment ini ! Momen Ordo 1 Untuk Mencari Pusat Objek

12 Contoh Perhitungan Moment
Tentukan Zeroth dan First Order Moment dari objek berikut ini:

13 Contoh Perhitungan Moment
Zeroth Order Moment Luas objek = A =m00 13 First Order Moment Posisi Objek (x,y) m10 = x = m01 = y =

14 Second Order Moment Digunakan untuk mencari orientasi atau kemiringan objek

15 Moments Invarian Moment dapat digunakan untuk menentukan karakteristik geometric dari sebuah objek Karakteristik ini bersifat invariant Tidak berubah walau objek mengalami transformasi Translasi Dilatasi Rotasi Refleksi Tujuh nilai moment yang menunjukkan karakteristik invariant (Hu, 1961)

16 http://www. codeproject

17 Tugas ‘ATM’ program berikut:

18 CONNECTED COMPONENT LABELLING

19 Apa itu Connected Component Labeling
Istilah lain connected-component analysis blob extraction region labeling blob discovery region extraction is an algorithmic application of graph theory, where subsets of connected components are uniquely labeled based on a given heuristic. Connected-component labeling is not segmentation. Connected-component labeling is used in computer vision to detect connected regions in binary digital images, although color images and data with higher-dimensionality can also be processed. When integrated into an image recognition system or human-computer interaction interface, connected component labeling can operate on a variety of information. Blob extraction is generally performed on the resulting binary image from a thresholding step. Blobs may be counted, filtered, and tracked.

20 Ilustrasi

21 Aplikasi: Aircraft Identification by Silhoute

22 Ilustrasi Cara Kerja CCL
In the beginning, we have this image, we start with currentLabelCount = 1.

23 Ilustrasi Cara Kerja CCL
Found non-background pixel

24 Ilustrasi Cara Kerja CCL
Gets its non-background pixel neighbours

25 Ilustrasi Cara Kerja CCL
Set the current pixel to the currentLabelCount and increment it , we also set the label's parent to itself

26 Ilustrasi Cara Kerja CCL
on to the next pixel, this one has a neighbour which is already labeled:

27 Ilustrasi Cara Kerja CCL
assigns the pixel's parent label to that of the neighbour

28 Ilustrasi Cara Kerja CCL
Continue on, none of the neighbours of this pixel is labeled:

29 Ilustrasi Cara Kerja CCL
We increment currentLabelCount and assign it to the pixel, again its parent is set to itself:

30 Ilustrasi Cara Kerja CCL
It gets interesting here, when neighbors have different labels:

31 Ilustrasi Cara Kerja CCL
Choose main label, i.e.: that would be the smallest label in the discovered list--> (1) Set it to be the parent of the other labels

32 Ilustrasi Cara Kerja CCL
Continue the process. Notice the blue number in the upper right corner, that's the parent label

33 Algorithm CCL First pass, assigning labels

34 Algorithm CCL Second pass, aggregating labels

35 8-CCL

36 Tugas ‘ATM ‘ program CCL

37 EULER NUMBER

38 What is Euler Number in Binary Image
Euler Number = the number of objects minus the number of holes.

39 Ilustrasi 7 objects 3 holes Euler = 4

40 Ilustrasi

41 Ilustrasi

42 Ilustrasi All the circles touch so they create one object. The object contains four "holes", which are the black areas created by the touching circles. Thus the Euler number is 1 minus 4, or -3.

43 The Euler Number is not a good shape descriptor.
About Euler Number The Euler Number is not a good shape descriptor.

44 Program CCL


Download ppt "Program Studi S-1 Teknik Informatika FMIPA Universitas Padjadjaran"

Presentasi serupa


Iklan oleh Google