project #5 and st ps - inf.u-szeged.hu - project 5...project database pipeline accuracy evaluation *...

11
19th Summer School on Image Processing Szeged - Hungary Project #5 and St ps Dávid Almási University of Debrecen Severino Gomes-Neto Federal University of Rio Grande do Norte Melinda Katona University of Szeged Tamás Sámuel Tasi University of Szeged

Upload: others

Post on 18-Oct-2019

2 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Project #5 and St ps - inf.u-szeged.hu - Project 5...Project Database Pipeline Accuracy Evaluation * Computing “out of the range” stairs as false positives. Actually, discarding

19th Summer School on Image ProcessingSzeged - Hungary

Project #5and St ps

DávidAlmásiUniversity

of Debrecen

SeverinoGomes-Neto

Federal University of

Rio Grande do Norte

MelindaKatonaUniversity

of Szeged

Tamás SámuelTasi

University

of Szeged

Page 2: Project #5 and St ps - inf.u-szeged.hu - Project 5...Project Database Pipeline Accuracy Evaluation * Computing “out of the range” stairs as false positives. Actually, discarding

Project

Page 3: Project #5 and St ps - inf.u-szeged.hu - Project 5...Project Database Pipeline Accuracy Evaluation * Computing “out of the range” stairs as false positives. Actually, discarding

Recognition of Doors and Steps

• Description– Appeal: Aid permanently or temporarily blind

people to know in advance the existence of doors and steps meanwhile they walk

– Input: Images from mobile phones (or webcams)

– Goal: recognize doors and steps

– Tools: Matlab R2010a + Image Processing Toolbox

Project Database Pipeline Accuracy Evaluation

Page 4: Project #5 and St ps - inf.u-szeged.hu - Project 5...Project Database Pipeline Accuracy Evaluation * Computing “out of the range” stairs as false positives. Actually, discarding

Database

Page 5: Project #5 and St ps - inf.u-szeged.hu - Project 5...Project Database Pipeline Accuracy Evaluation * Computing “out of the range” stairs as false positives. Actually, discarding

Actual PicturesProject Database Pipeline Accuracy Evaluation

StairsNon stairs

Page 6: Project #5 and St ps - inf.u-szeged.hu - Project 5...Project Database Pipeline Accuracy Evaluation * Computing “out of the range” stairs as false positives. Actually, discarding

Actual PicturesProject Database Pipeline Accuracy Evaluation

DoorsNon doorsNon stairs

Page 7: Project #5 and St ps - inf.u-szeged.hu - Project 5...Project Database Pipeline Accuracy Evaluation * Computing “out of the range” stairs as false positives. Actually, discarding

Pipeline

Page 8: Project #5 and St ps - inf.u-szeged.hu - Project 5...Project Database Pipeline Accuracy Evaluation * Computing “out of the range” stairs as false positives. Actually, discarding

Recognizing StepsProject Database Pipeline Accuracy Evaluation

Input Image

Gray Scaled

Crop

Histogram Equalization

Sharpening

Fourier Transform

Output Steps!

Edge Detection

Page 9: Project #5 and St ps - inf.u-szeged.hu - Project 5...Project Database Pipeline Accuracy Evaluation * Computing “out of the range” stairs as false positives. Actually, discarding

Recognizing DoorsProject Database Pipeline Accuracy Evaluation

Input Image

Gray Scaled

Crop

Histogram Equalization

Sharpening

Fourier Transform

Output Door!

Edge Detection

Page 10: Project #5 and St ps - inf.u-szeged.hu - Project 5...Project Database Pipeline Accuracy Evaluation * Computing “out of the range” stairs as false positives. Actually, discarding

Accuracy Evaluation

Page 11: Project #5 and St ps - inf.u-szeged.hu - Project 5...Project Database Pipeline Accuracy Evaluation * Computing “out of the range” stairs as false positives. Actually, discarding

Positives and Negatives

Positives Negatives

StepsTrue 16 (89%) 8 (44%)*

False 2 (11%) 10 (56%)*

DoorsTrue 10 (83%) 2 (50%)

False 2 (17%) 2 (50%)

Project Database Pipeline Accuracy Evaluation

* Computing “out of the range” stairs as false positives.

Actually, discarding those, the results are:8 true negatives (73%) and 3 false negatives (27%)