Spelling suggestions: "subject:"fontrecognition"" "subject:"andrecognition""
321 |
Recurrent neural network-enhanced HMM speech recognition systemsThirion, Jan Willem Frederik 31 October 2005 (has links)
Please read the abstract in the section 00front of this document / Dissertation (MEng (Electronic Engineering))--University of Pretoria, 2006. / Electrical, Electronic and Computer Engineering / unrestricted
|
322 |
Analysis and design of cryptographic hash functionsKasselman, Pieter Retief 20 December 2006 (has links)
Please read the abstract in the section 00front of this document. / Dissertation (M Eng (Electronic Engineering))--University of Pretoria, 2006. / Electrical, Electronic and Computer Engineering / unrestricted
|
323 |
Automata theoretic aspects of temporal behaviour and computability in logical neural networksLudermir, Teresa B. January 1991 (has links)
No description available.
|
324 |
An Image Processing and Pattern Analysis Approach for Food RecognitionPouladzadeh, Parisa January 2013 (has links)
As people across the globe are becoming more interested in watching their weight, eating more healthily, and avoiding obesity, a system that can measure calories and nutrition in everyday meals can be very useful. Recently, there has been an increase in the usage of personal mobile technology such as smartphones or tablets, which users carry with them practically all the time. In this paper, we proposed a food calorie and nutrition measurement system that can help patients and dieticians to measure and manage daily food intake. Our system is built on food image processing and uses nutritional fact tables. Via a special calibration technique, our system uses the built-in camera of such mobile devices and records a photo of the food before and after eating it in order to measure the consumption of calorie and nutrient components. The proposed algorithm used color, texture and contour segmentation and extracted important features such as shape, color, size and texture. Using various combinations of these features and applying a support vector machine as a classifier, a good classification was achieved and simulation results show that the algorithm recognizes food categories with an accuracy rate of 92.2%, on average.
|
325 |
The Multimodal Interaction through the Design of Data GloveHan, Bote January 2015 (has links)
In this thesis, we propose and present a multimodal interaction system that can provide a natural way for human-computer interaction. The core idea of this system is to help users to interact with the machine naturally by recognizing various gestures from the user from a wearable device. To achieve this goal, we have implemented a system including both hardware solution and gesture recognizing approaches. For the hardware solution, we designed and implemented a data glove based interaction device with multiple kinds of sensors to detect finger formations, touch commands and hand postures. We also modified and implemented two gesture recognizing approach based on support vector machine (SVM) as well as the lookup table. The detailed design and information is presented in this thesis. In the end, the system achieves supporting over 30 kinds of touch commands, 18 kinds of finger formation, and 10 kinds of hand postures as well as the combination of finger formation and hand posture with the recognition rate of 86.67% as well as the accurate touch command detection. We also evaluated the system from the subjective user experience.
|
326 |
Human Action Recognition from Gradient Boundary HistogramsWang, Xuelu January 2017 (has links)
This thesis presents a framework for automatic recognition of human actions in un- controlled, realistic video data with fixed cameras, such as surveillance videos. In this thesis, we divide human action recognition into three steps: description, representation, and classification of local spatio-temporal features. The bag-of-features model was used to build the classifier. Fisher Vectors were also studied. We focus on the potential of the methods, with the joint optimization of two constraints: the classification precision and its efficiency.
On the performance side, a new local descriptor, called Gradient Boundary Histograms (GBH), is adopted. It is built on simple spatio-temporal gradients, which can be computed quickly. We demonstrate that GBH can better represent local structure and motion than other gradient-based descriptors, and significantly outperforms them on large datasets. Our evaluation shows that compared to HOG descriptors, which are based solely on spatial gradient, GBH descriptor preserves the recognition precision even in difficult situation.
Since surveillance video captured with fixed cameras is the emphasis of our study, removing the background before action recognition is helpful for improving efficiency. We first preprocess the video data by applying HOG to detect humans. GBH descriptor is then used at reduced spatial resolutions, which yields both high efficiency and low memory usage; in addition, we apply PCA to reduce the feature dimensions, which results in fast matching and an accelerated classification process.
Experiments our methods achieved good performance in recognizing precision, while simultaneously highlighting effectiveness and efficiency.
|
327 |
An experimental system for recognizing typewritten charactersFletcher, Thomas Ralph January 1970 (has links)
An optical character recognition system was developed using the Lexiphone, a direct-translation reading machine for the blind, interfaced to a digital computer. The system was designed to read alphanumeric typewritten characters. In the development stages one serifed type-style was used exclusively. Three additional different, but serifed, type-styles were also used.
Classification was performed by a method referred to as "component deletion". This method extends a nearest neighbours classification scheme enabling feature vectors differing in length by one two-bit segment to be compared by making their dimensionality the same. The method includes the classification of equal length vectors. The component deletion technique provided similar results to exact matching yet required significantly less training.
Using carbon ribbon print, recognition was better than 92% for the four type-styles combined. The use of cloth ribbon for the type-style used in the development lowered recognition by a few percent. / Applied Science, Faculty of / Electrical and Computer Engineering, Department of / Graduate
|
328 |
A reexamination of the role of the hippocampus in object-recognition memory using neurotoxic lesions and ischemia in ratsDuva, Christopher Adam 11 1900 (has links)
Paradoxical results on object-recognition delayed nonmatching-to-sample (DNMS)
tasks have been found in monkeys and rats that receive either partial, ischemia-induced
hippocampal lesions or complete hippocampal ablation. Ischemia results in severe DNMS
impairments, which have been attributed to circumscribed CA1 cell loss. However,
ablation studies indicate that the hippocampus plays only a minimal role in the performance
of the DNMS task. Two hypotheses have been proposed to account for these discrepant
findings (Bachevalier & Mishkin, 1989). First, the "hippocampal interference" hypothesis
posits that following ischemia, the partially damaged hippocampus may disrupt activity in
extrahippocampal structures that are important for object-recognition memory. Second,
previously undetected ischemia-induced extrahippocampal damage may be responsible for
the DNMS impairments attributed to CA1 cell loss.
To test the "hippocampal interference" hypothesis, the effect of partial NMDAinduced
lesions of the dorsal hippocampus were investigated on DNMS performance in
rats. These lesions damaged much of the same area, the CA1, as did ischemia; but did so
without depriving the entire forebrain of oxygen, thereby reducing the possibility of
extrahippocampal damage. In Experiment 1, rats were trained on the DNMS task prior to
receiving an NMDA-lesion. Postoperatively, these rats reacquired the nonmatching rule at
a rate equivalent to controls and were unimpaired in performance at delays up to 300 s. In
Experiment 2, naive rats were given NMDA-lesions and then trained on DNMS. These
rats acquired the DNMS rule at a rate equivalent to controls and performed normally at
delays up to 300 s. These findings suggest that interference from a partially damaged
hippocampus cannot account for the ischemia-induced DNMS impairments and that they
are more likely produced by extrahippocampal neuropathology. In Experiment 3, rats from
the previous study were tested on the Morris water-maze. Compared to sham-lesioned
animals, rats with partial lesions of the dorsal hippocampus were impaired in the
acquisition of the water-maze task. Thus, subtotal NMDA-lesions of the hippocampus
impaired spatial memory while leaving nonspatial memory intact.
Mumby et al. (1992b) suggested that the ischemia-induced extrahippocampal
damage underlying the DNMS deficits is mediated or produced by the postischemic
hippocampus. To test this idea, preoperatively trained rats in Experiment 4 were subject to
cerebral ischemia followed within 1hr by hippocampal aspiration lesions. It was
hypothesized that ablation soon after ischemia would block the damage putatively produced
by the postischemic hippocampus and thereby prevent the development of postoperative
DNMS deficits. Unlike "ischemia-only" rats, the rats with the combined lesion were able to
reacquire the nonmatching rule at a normal rate and performed normally at delays up to 300
s. Thus, hippocampectomy soon after ischemia eliminated the pathogenic process that lead
to ischemia-induced DNMS deficits. Experiment 5 investigated the role of ischemiainduced
CA1 cell death as a factor in the production of extrahippocampal neuropathology.
Naive rats were given NMDA-lesions of the dorsal hippocampus followed 3 weeks later by
cerebral ischemia. If the ischemia-induced CA1 neurotoxicity is responsible for producing
extrahippocampal damage then preischemic ablation should attenuate this process and
prevent the development of DNMS impairments. This did not occur: Rats with the
combined lesion were as impaired as the "ischemia-only" rats in the acquisition of the
DNMS task. This suggests that the ischemia-induced pathogenic processes that result in
extrahippocampal neuropathology comprise more than CA1 neurotoxicity.
The findings presented in this thesis are consistent with the idea that ischemiainduced
DNMS deficits in rats are the result of extrahippocampal damage mediated or
produced by the postischemic hippocampus. The discussion focuses on three main points:
1) How might the post-ischemic hippocampus be involved in the production of
extrahippocampal neuropathology? 2) In what brain region(s) might this damage be
occurring? 3) What anatomical, molecular, or functional neuropathology might ischemia
produce in extrahippocampal brain regions? The results are also discussed in terms of a
specialized role for the hippocampus in mnemonic functions and the recently emphasized
importance of the rhinal cortex in object-recognition memory. / Arts, Faculty of / Psychology, Department of / Graduate
|
329 |
Detection of frequency and intensity changes using synthetic vowels and other soundsCosgrove, Paul January 1988 (has links)
No description available.
|
330 |
Strata recognition from computer analysis of drilling variablesGriffiths, C. M. January 1983 (has links)
No description available.
|
Page generated in 0.1701 seconds