Sinhala Alphabet - Download as PDF File .pdf), Text File .txt) or view presentation slides online. sin. The simplest letter in the Sinhala sometimes touch each other and they also have variations in alphabet is known to as “ර”, which is also specified as the writing. Details of the Sinhala alphabet and language, which is spoken mainly in Sri Lanka by about 12 million people.
|Language:||English, Spanish, German|
|Genre:||Fiction & Literature|
|ePub File Size:||15.88 MB|
|PDF File Size:||11.86 MB|
|Distribution:||Free* [*Regsitration Required]|
Basic Sinhala is a beginning course presented in three modules dealing with the written in the Sinhala alphabet, this module must be undertaken first. H. The Sinhalese alphabet, which is one of the Brahmic scripts, a descendant of the ancient Indian Brahmi script .. Official Unicode Consortium code chart (PDF). Sinhala script (Sinhala: සිංහල අක්ෂර මාලාව) (Siṁhala Akṣara Mālāva) is a writing The core set of letters forms the śuddha siṃhala alphabet (Pure Sinhala , ශුද්ධ සිංහල), which is Official Unicode Consortium code chart (PDF).
This is because Sinhala used to be written on dried palm leaves , which would split along the veins on writing straight lines. The Sinhala alphabet, a descendent of the Brahmi script, started to appear in inscriptions during the 3rd and 2nd centuries BC. Depending on the vowel, the diacritic can attach at several places. Sinhalese authors reading extracts from their work: CS1 errors: Itis one of the official and national more strokes positioned around the consonant.
Most of the proposed techniques use the horizontal Unlike printed character recognition, in handwritten projection profile for line extraction , . Also for text character recognition, the difficulty of correct segmentation of lines with variation in the skew angle between text lines, characters is always at hand. Correctness in segmentation is a Hough based methods has been proposed . Most of the work done has made character groups according to the way they touch each other: Among the four groups the connecting variety gaps between words.
Among other three, the The approach of using Hidden Markov Modelswhich is overlapping and touching character occurrences are more proposed for Sinhala handwritten character recognition can be common than intersecting characters in ordinary practice. But the method proposed in  does not Among the two parameters of the dimensions of a letter, accommodate for the full Sinhala alphabet.
In  line width and height, width has more prominence in the context of extraction has been done using the zero values in the projection character segmentation. The selected set of Sinhala letters can profile correspond to horizontal gaps between lines.
It has been be categorized in to two main categories according to their used a pre-formatted paper to collect handwriting, which width. Table 1 shows the categorization according to the width. Then the II. But this research The challenging nature of handwritten character recognition work has not addressed the possibilities of touching characters has drawn the attention of researches for a long time all over in the text and segmentation of the touching characters.
The work presented by M. M Karunanayaka, N. D These researches have explored many areas available in Kodikara, and G. P Wimalaratne in  has addressed the like the computational pattern recognition area with issue of touching characters.
At the beginning, they have techniques such as artificial neural networks  and segmented the images using vertical projection profile method statistical approaches such as Hidden Markov Models  and at that level the touching characters are considered as a to recognize handwritten words or characters.
The first step single entity. Touching character groups, a overlapping, b touching, c intersecting, and d connecting Figure 2. The unsteady nature of Then the segmented character entities are further classified handwritten characters make the recognition task difficult. The between two categories: In the process the average character width has been characters is a key factor to the accuracy of the character estimated using the width of the image and number of recognition process.
This research will be focused segmenting characters occurs in that image which is obtained from the Sinhala handwritten documents in to lines, words and vertical projection profile as given in 1. Twenty three characters from the Sinhala alphabet given in Fig. The twenty four characters do not include the vowel signs as well as less frequently used characters. It is assumed that the characters of two consecutive text lines are not touching or overlapping and there is no slant in the text lines.
After distinguishing touching characters, the touching character group has been identified and segmented. Connected V. To distinguish and how the line segmentation, word segmentation, character between the other three groups, the concept known as Water segmentation and segmentation of touching characters were Reservoir Conceptdiscussed in  has been used.
Preprocessing trained using unsupervised learning. SOFMs facilitate A4 size papers were used for collecting handwriting representing multidimensional data using much lower samples. All the sample documents included 5 — 10 lines. The dimensional space. Also it creates a network that stores documents were scanned to get the images required for information in such a way that it represents the topological processing.
The images were converted in to binary format relationships of the training samples. The points that are close using OTSU  thresholding mechanism.
Line segmentatiom analyzing tool of high dimensional data. It is assumed that characters of two consecutive text lines are not touching or overlapping. With that assumption the There is no related work to be found in Sinhala image is segmented in to lines using the horizontal projection handwritten character segmentation with SOMFs.
The work profile. The main idea behind their proposal is that If the characters of two consecutive text lines are not the touching pairs can be divided in to three main regions: The authors believe that these regions have projection profile correspond to the white space between the unique characteristics and by mapping the touching characters lines. Word Segmentation The basic steps of the method proposed in  are, Each of the segmented lines goes through the word segmentation process.
The assumption that the characters of 1 Estimating the core zone of the characters two words are not touching each other was made.
With that 2 Extraction of feature points as input to SOFM assumption vertical projection profile was calculated for each 3 Determining segmentation path line segment. An example of the vertical projection profile of two text lines are given in Fig. Use of horizontal projection profile for line segmentation As the gap between two characters within a word is The method proposed in  using SOFMs will then be relatively smaller than the gap between two words, a threshold used to segment the touching characters.
I Core zone estimation The ascender and descender components of the characters D. Basic Character segmentation will be removed in order to get the core zone of the characters.
Each word segmented goes through the character As suggested by Kurniawan F. Again, vertical projection profile was is done in order to improve the clustering process . Touching Character segmentation III Feature extraction and using SOFM for clustering The touching characters should be identified at first before The simple feature extraction method will be used to moving in to the segmentation process.
To identify a touching generate the feature vector.
Number of maximum feature character, a similar approach to  has been used. After points will be taken as a variable parameter. The touching distinguishing touching characters, connected component character segment is scanned from left to right within the core labeling has been used to identify the presence of overlapping zone to generate the feature vector. In the connected component According to the number of maximum feature points, some labeling process, if there are more than two labels present, each of the foreground pixels will be selected to generate the feature connected component is considered as a single character.
The vector. Then the feature vector will be clustered to segment the remaining segments which are gained only one label in the touching pair using the SOFM.
To do that the architecture of connected component labeling are recognized as touching the SOFM will be configured as one dimensional layer having characters. The three neuron nodes are devoted to the left middle and right regions respectively. During training, each node will be getting closer to the three regions.
FUTURE WORK The proposed method for identifying a touching character After this clustering process the segmentation of the in  can be improved using widths categories of the letters of touching pairs can be performed based on the Position of the the considered Sinhala letters. An average character width for middle neuron node.
With the assumption of the text lines does not have a slant angle, a vertical line is considered as the each of the two width categories can be calculated and after segmentation path. Languages by writing system Language index Alternative scripts Phonetic alphabets Other notation systems Language-based communication systems Magical alphabets Con-scripts Also used to write Pali and Sanskrit in Sri Lanka. Sinhala alphabet Vowels Are you a developer?
Documents Similar To Sinhala Alphabet. Jeeva Ellapillai. Abdul Shakur Faisal. Jesus Lives. Geethu Mohan. Gilmar Iria. Prasad Sachidananda. Anny Khan. Amy Li.
Rodolfo Minhoto. Robert Tucker. German Antonio Tejeda Puentes. Vadivu Mahes. Kolaveri Di. Anthony Carrion. Abie Badhurahman. Python versus Matlab: Vee Ezwin. More From Sivapalasundaram Raghuram.
Sivapalasundaram Raghuram. Inhalers by J.
Popular in Business. Mania Pauldoe. Fred Msumali. Cluisantony Jayco Dize. Albertho Statesman.
Shashank Gupta. Christine Elaine Batusin Ilagan.
April Jhesica Viloria Dajugar. Elizabeth Perry Muderick. Ajay Singh. Roberto Perez. Jose Francisco Arteaga Riquelme. Rajendra Prasad Shukla.
Marvic Oquindo Unay. Swathi Raman.