Geri Dön

Fisher kernel based models for image classification and object localization

Başlık çevirisi mevcut değil.

  1. Tez No: 401572
  2. Yazar: RAMAZAN GÖKBERK CİNBİŞ
  3. Danışmanlar: DR. CORDELIA SCHMID, DR. JAKOB VERBEEK
  4. Tez Türü: Doktora
  5. Konular: Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrol, Computer Engineering and Computer Science and Control
  6. Anahtar Kelimeler: Belirtilmemiş.
  7. Yıl: 2014
  8. Dil: İngilizce
  9. Üniversite: Université de Grenoble
  10. Enstitü: Yurtdışı Enstitü
  11. Ana Bilim Dalı: Belirtilmemiş.
  12. Bilim Dalı: Belirtilmemiş.
  13. Sayfa Sayısı: 181

Özet

Özet yok.

Özet (Çeviri)

In this dissertation, we propose models and methods targeting image understanding tasks. In particular, we focus on Fisher kernel based approaches for the image classification and object localization problems. We group our studies into the following three main chapters. First, we propose novel image descriptors based on non-i.i.d. image models. Our starting point is the observation that local image regions are implicitly assumed to be identically and independently distributed (i.i.d.) in the bag-of-words (BoW) model. We introduce non-i.i.d. models by treating the parameters of the BoW model as latent variables, which renders all local regions dependent. Using the Fisher kernel framework we encode an image by the gradient of the data loglikelihood with respect to model hyper-parameters. Our representation naturally involves discounting transformations, providing an explanation of why such transformations have proven successful. Using variational inference we extend the basic model to include Gaussian mixtures over local descriptors, and latent topic models to capture the co-occurrence structure of visual words. Second, we present an object detection system based on the high-dimensional Fisher vectors image representation. For computational and storage efficiency, we use a recent segmentation-based method to generate class-independent object detection hypotheses, in combination with data compression techniques. Our main contribution is a method to produce tentative object segmentation masks to suppress background clutter in the features. We show that re-weighting the local image features based on these masks improve object detection performance significantly. Third, we propose a weakly supervised object localization approach. Standard supervised training of object detectors requires bounding box annotations of object instances. This time-consuming annotation process is sidestepped in weakly supervised learning, which requires only binary class labels that indicate the absence/ presence of object instances. We follow a multiple-instance learning approach that iteratively trains the detector and infers the object locations. Our main contribution is a multi-fold multiple instance learning procedure, which prevents training from prematurely locking onto erroneous object locations. We show that this procedure is particularly important when high-dimensional representations, such as the Fisher vectors, are used. Finally, in the appendix of the thesis, we present our work on person identification in uncontrolled TV videos. We show that cast-specific distance metrics can be learned without labeling any training examples by utilizing face pairs within tracks and across temporally-overlapping tracks. We show that the obtained metrics improve face-track identification, recognition and clustering performances. Keywords Image classification, object detection, weakly supervised training, computer vision, machine learning.

Benzer Tezler

  1. Open-set object recognition

    Açık-set nesne tanıma

    SALMAN MOHAMMAD

    Yüksek Lisans

    İngilizce

    İngilizce

    2022

    Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrolİhsan Doğramacı Bilkent Üniversitesi

    Bilgisayar Mühendisliği Ana Bilim Dalı

    DR. ÖĞR. ÜYESİ SHERVIN RAHIMZADEH ARASHLOO

  2. Avuç izine dayalı kimliklendirme sistemlerinde kısıtlamasız aya örüntüsü çıkarımı ve uygulaması

    Unrestricted palm pattern selection and implementation on palmprint based identification systems

    ELİF BAYKAL

    Yüksek Lisans

    Türkçe

    Türkçe

    2015

    Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve KontrolKaradeniz Teknik Üniversitesi

    Bilgisayar Mühendisliği Ana Bilim Dalı

    DOÇ. DR. MURAT EKİNCİ

  3. Esnek kullanımlı avuç izi bölgesine dayalı doğrulama sistemlerinin tasarım çalışması

    A comprehensive study on flexible palmprint verification system design

    MURAT AYKUT

    Doktora

    Türkçe

    Türkçe

    2013

    Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve KontrolKaradeniz Teknik Üniversitesi

    Bilgisayar Bilimleri Ana Bilim Dalı

    DOÇ. MURAT EKİNCİ

  4. Vision based sign language recognition: Modeling and recognizing isolated signs with manual and non-manual components

    Video tabanlı işaret dili tanıma: El ve el dışı hareketler içeren ayrık işaretlerin modellenmesi ve tanınması

    OYA ARAN

    Doktora

    İngilizce

    İngilizce

    2008

    Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve KontrolBoğaziçi Üniversitesi

    Bilgisayar Mühendisliği Bölümü

    PROF. LALE AKARUN

  5. A comparison of subspace based face recgnition methods

    Alt-uzay tabanlı yüz tanıma yöntemlerinin karşılaştırılması

    ÖZKAN GÖNDER

    Yüksek Lisans

    İngilizce

    İngilizce

    2004

    Elektrik ve Elektronik MühendisliğiOrta Doğu Teknik Üniversitesi

    Elektrik-Elektronik Mühendisliği Ana Bilim Dalı

    PROF. DR. UĞUR HALICI