The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
We present a plant image recognition system geared towards plants with flowers. The system uses local invariants with Dense SIFT features and Bag of Visual Words representation, while the classification is done using Support Vector Machines. Our approach contains a pre-classification stage where images are categorized into color subgroups, to reduce the complexity of the problem. Using a 161-class...
This paper proposes a cheap image processing method for visual compass in the robot soccer context. An offline map is constructed by using color transition histogram features. When a feature is extracted, we calculate maximum likelihood orientation of that feature over the pre-calculated map. This instantaneous orientation information updates orientation belief with given mixing constant. We presented...
Online textual and visual data that are created and used by web users have been increasing dramatically and continually. This increase has caused the need for easy and fast access to online data and facilitated the development of alternative means of access to this data. Nowadays, web crawlers are the most efficient and popular tools used for accessing big volumes of data available on the web. In...
The goal of this study is to explore the advantages of representing natural images with the cortical Layer-4 processing, which is the first step in visual information processing performed by the cerebral cortex of the brain. A cortical module, a macrocolumn, receives input from a small visual field and its Layer 4 performs a nonlinear transform of this input to generate its pluripotent representation...
In this work, we study the understanding of 3D visual objects which are generated by augmented reality techniques. 3D glasses are typically highly priced, and so they are not purchasable for most consumers. Instead, we consider low-priced red-cyan (anaglyph) glasses. We generate the left and right views so that they are comfortable for human eyes.
When image labeling (annotation) process for image retrieval is performed by fully automatic algorithms, labels have noise, errors and missing labels. Correcting labels gathered automatically from web (using information around an image such as text, user-tags, etc.) is done manually using human labor. Therefore, coordination of different indivuduals is necessary for a consistent annotation. In this...
Automatic separation of defective eggs from qualified eggs reduces visual control difficulties which are done using human power as well as ensures improvement on the quality control process. In this paper, eggs are classified as dirt eggs, crack eggs and clean eggs as well as separation of defective eggs from qualified eggs. Hybrid solution is applied for detection defects on eggshell. Firstly, egg...
Exposure Fusion is a popular multi-exposure image fusion method which blends a set of differently exposed low dynamic range images of a scene to obtain another low dynamic range but contrast rich image. This approach carries out the integration process by using three local quality measures, namely contrast, saturation and exposedness. Our aim in this study is to extend the exposure fusion method by...
This work is part of a project for imitation based turn-taking and interaction games for children with communication impairments. The paper focuses on a music based interaction game mainly for children with autism. Autism Spectrum Disorder (ASD) involves communication impairments, limited social interaction, and limited imagination. Music can facilitate social interaction between the child and teacher/parent...
Hyperspectral imaging captures a high number of spectrally narrow bands and provides advantages for image analysis applications such as identification and classification in particular. However, for the visual inspection of hyperspectral images, the data is conventionally converted to a standard color image format. It is important that as much detail and data as possible is retained during this conversion...
In this study, it is aimed to follow a visual route by an Unmanned Aerial Vehicle (UAV). The recognition of the predetermined line by using image processing algorithms and the process of following the route by using the method of Tangent Vector Field Guidance (TVFG) have been performed in indoor and outdoor experiments. UAV s following the correct route has been ensured by calculating the deflection...
In this study, the degree of connectivity for each voxel, which is the unit element of functional Magnetic Resonance Imaging (fMRI) data, with its neighboring voxels is estimated. The neighborhood system is defined by spatial connectivity metrics and a local mesh of variable size is formed around each voxel using spatial neighborhood. Then, the mesh arc weights, called Mesh Arc Descriptors (MAD),...
This study aims at presenting an emotional corpus collected at Bog˘aziçi University / Electrical and Electronics Department, on which no previous signal processing and machine learning study was done for classification purposes. It also aims at providing the protocol for further experiments on this corpus. The emotional corpus consists of 484 speech utterances from 11 amateur actors acting 11 emotionally...
In this paper we propose a new hyperplane fitting classification method that does not have limitations of the existing hyperplane fitting classifiers. There are two principal improvements of the proposed method: It returns sparse solutions and it is suitable for large-scale problems. Both advantages are accomplished by using a simple trick, which constraints positive samples to lie between two parallel...
In this paper the influence of vibrotactile stimuli on the evaluation of loudness of speech is investigated. The speech utterances consisted of context-free consonant-vowel-consonant (CVC) and vowel-consonant-vowel (VCV) utterances played over headphones on a mobile phone. The phone's standard vibration was used as the tactile stimulus. Using an AB/X paradigm, 32 untrained subjects evaluated loudness...
The Signals and Systems Concept Inventory is an extremely useful assessment tool that has been widely used and analyzed. The authors have applied it in a variety of situations outside its typical usage. These situations include comparing international students to US students, introducing concept inventories to international faculty, supporting an ABET evaluation report, evaluating the effect of electives...
Two ongoing challenges facing instructors when designing courses are (1) do students identify/understand important concepts in the course, and (2) what makes concepts difficult for students to understand? In particular, do students see the relationship between the procedures taught and the fundamental concepts they support? In this study, we use interviews with 39 undergraduate engineering students...
This paper examines the exact solution for combining multiple Gaussian mixture (GM) estimates of a state vector, methods for order-reduction of the resulting GM, estimating the likelihood of each source GM, and for classifying sources as good (in agreement) or bad (biased or false/spoofed). Together, these allow combining estimates from GM sources in a way that guarantees some false-rejection probability...
This paper presents an architecture to support fast prototyping of augmented reality systems, based on virtual reality. The architecture defines simulation services separated from other aspects of the system. These services support incremental evolution of simulated prototypes into nonsimulated systems. Focus is also placed on user interaction,through the definition of an interaction architecture...
Video segmentation is the first and critical step in video indexing and retrieval. Previous work in this area has primarily focused on visual and audio information. In this paper, we investigate the segmentation of documentary video data through audio and text understanding. To segment a continuous documentary video stream into subtopic segments, music markers and domain-independent video speech text...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.