The various fieldsand applications can be analyzed by using digital image processing. Inagriculture sector the quality and quantity are the important measures from thefarmers perspective. Soil is the one of most important valuable resource . Soil pH is used to measure the acidityand alkalinity in soils.
The soil pH value of 7.0 is referred asneutral, soil above this value is called as alkaline and soil belove this value is called as acidic. Soilsamples were collected and their pH was determined by using PCA algorithm. Keywords—component;formatting; style; styling; insert (key words) I. Introduction (Heading 1)Soil is recognized as one of themost valuable natural resource.
Soils are considered as the integral part ofthe landscape and their characteristics are largely governed by the landformson which they have developed .Systematic study of soils provides information onnature and type of soils for various uses. The pH in soils is an importantconcerning part of the soil health. pH is a term that is used to describe the degreeof acidity or basicity.
Soil acidity or alkalinity directly affects plantgrowth. If a soil is too sour or too sweet, plants cannot take up nutrientslike nitrogen (N), phosphorus (P) and potassium (K). Most nutrients that plantsneed are readily available when the pH of the soil solution ranges from 6.0 to7.
5. Below a pH of 6.0 (acid): Some nutrients such as nitrogen, phosphorus, andpotassium are less available. Above a pH of 7.5 (very alkaline), Iron,manganese, and phosphorus are less available.
Asoil with a pH of 6.0 is ten times more acidic than a soil of pH 7.0. Changes insoil pH dramaticallyaffect the availability of nutrients to growingcrops.
The pH meter is the preferred methodfor determination of soil pH. A soilanalysis is a process by which elements such as P, K, Ca, MG, Na, S, Mn, Cu, Znare chemically extracted from the soil and measured for there “plant available” content within the soil sample. The soil pH reflect whether a soil is acidic,basic or alkaline. The acidity, neutrality or alkalinity of a soil is measuredin terms of hydrogen ion activity of the soil water system .The negativelogarithm of the H ion activity is called pH and thus pH of a soil is a measureof only the intensity of activity and not the amount of acid present. The pHrange normally found in soil varies from 3 to 9 . Mathematically pH is representedas ,log 1/H= log H+ Following table shows soil pH and Interpretation The soil pH can be determined from soil color using ondigital image processing techniques.
in which digital photographs of the soilsamples were used for the analysis of soil pH. Soil color is visual perceptualproperty corresponding in humans to the categories i.e. red, green, blue andothers. Soil colors are the parts of visual perceptual property where digitalvalues of red, green and blue (RGB) provide a clue for spectral signaturecapture of different pH in soil.
1. DeterminationOf Soil Ph And Nutrient Using Image ProcessingSoil samples were collected and their pH was determined by usingdigital image processing technique. Soil colour is visual perceptual propertycorresponding in humans to the categories i.e red, green, blue and others. Soilcolours are the parts of visual perceptual property where digital values ofred, green and blue (RGB) provide a clue for spectral signature capture ofdifferent pH in soil.
For the capturing images, digital camera was used. On thebasis of RGB grey values, pixels properties and their digital correlations,results showed that there was a clear cut gap in grey values of colours in theimages . Ranges of soil pH and pH index values were 7.30-7.
50 and0.0070-0.0261, respectively in deep brown colour. Similarly, soil pH rangevaries from 6.80-7.04 and 5.
58-6.58 in light yellowish and greenish colourrespectively while their corresponding pH index values were 0.0071-0.
0451 and0.0084-0.0239. Thus soil pH range varies from 7.
04 and5.58-6.58 in deep brown colour, light yellowish colour and greenish colourrespectively.
2. Soil Salinity Mapping and Monitoring inArid and Semi-Arid Regions Using Remote Sensing TechnologyA statisticalanalysis was performed on three thousand and eight hundred soil sample datafrom Thrissur district. Soil pH, Electrical conductivity, Organic Carbon, Phosphorus,Potassium, Calcium, Magnesium, Sulfur, Zinc, Boron, Iron, Copper and Manganesedata were analyzed.Correlationanalysis, ANOVA and Principal Component analysis were performed on the dataset. Analysis indicate that different soil components are significantlycorrelated with soil properties. 3. Testingof Agriculture Soil by Digital Image Processing Generallysoil pH is measured manually in Government Labs.
There are various labs butinstrument used for this is not available everywhere. So we need to implementcalculation of soil pH by using digital Image Processing. Eighty soil sampleswere collected and their pH firstly tested in Government Soil Testing Lab,Agriculture College Nagpur and also it was determined by using digital imageprocessing technique. On the basis of RGB values, pixels properties and theirdigital correlations, results showed that our pH values were approximatelymatching with results from Government Testing lab.4. SoilCharacterization Based on Digital Image AnalysisThe digital imagedatabase is prepared for the collected soil sample in the laboratory andphysical properties(Y) are determined.
Digital image analysis is adopted toestimate the image feature namely fractal dimension (X). Correlation isdeveloped between Y and X by fittingappropriate polynomial equations using regression models.The final results of this research will contribute to make soil physicalproperties estimation automatic up to a certain degree of level, which willassist to a geotechnical engineers, in soil classification. The results ofpresent work emphasizes that there is a great potential in the use of fractaldimension for estimating physical soil properties for practical application, withminimum human error. II.
MethodologyTheprocessing scheme consists of image acquisition through digital camera orscanner or mobile phone. Image processing includes image enhancement, filteringof image to remove noise etc .image segmentation, feature extraction andDetection.
In the proposed work to design the system, training dataset andtest images are considered. The training dataset is the raw data which haslarge amount of data stored in it and the test image is the input given forrecognition purpose. Stepsinvolved in designing are as follow 1.
ImageAcquisitionIn any of the image processing techniques the firsttask is to acquire the image from the source. These images can be acquiredeither through camera or through standard datasets that are available online.The images should be in .jpg format. The images considered are user dependent.
2. Pre-processingPre-processingis mainly done to eliminate the unwanted information from the image acquiredand fix some values for it, so that the value remains same throughout. In thepre-processing phase the images are converted from RGB to Gray-scale and areresized to 512*512 pixels. The images considered are in .
jpg format, any otherformats found will not be considered for further processing. Duringpre-processing, whole face is considered to be the region of interest. It isdetected by the cascade object detector which utilizes Jones-Viola algorithm.
3. SegmentationSegmentation means partitioning of images into variouspart or region and extracting meaningful region known as region of interest(ROI).The level to which subdivision is carried depends on the problem beingsolved .Segmentation can be stopped when the region of interest in anapplication havebeen isolated. Segmentation accuracy determines success orfailure of computerized analysis procedures.
So algorithm picked forsegmentation should perform best for given requirement.4. SoilFeature Extraction After pre-processing the nextstep is feature extraction. The extracted Soil features are stored as theuseful information in the form of vectors during training phase and testingphase. There are various methods for extracting the Soil features some of whichare as listed below:1. Knowledgebased Method: It is a rule based method that takes the knowledge of faces andbuilds certain rules.2. Geometricbased Method: It extracts the features based on the sizes and positions of thecomponents from an image.
3. Templatebased Method: With the appropriate energy function, features are extracted fromprevious template and the one that matches best yields minimum energy. 4. Colorbased Method: It takes skin color into account to bifurcate between the faceregion and non face region from an image.
5. Appearancebased Method: They represent important parts of the face because of theirholistic nature which deals with whole face. Here methods like PCA or ICA areused to extract the Soil features. Among all the above mentioned methods the one that isused in the proposed work is PCA method for the reason that: it requires lessmemory and storage capacity as the operation is carried out in a space ofsmaller dimensions which also helps in increasing the efficiency of the system.It is independent from the Soil geometry like size and shape of the face. Thepossibility of real-time realization without even making use of any specialhardware’s like sensors or EEG equipment.
It is easy to use and gives highspeed of recognition as compared to other methods. It gives higher success ratein comparison with other methods.A. PCA ALGORITHMPrincipal component analysis (PCA) or karhunen-loeve transformation isa statistical approach used for pattern recognition and signalprocessingto reduce the number of variables in face recognition technique. PCAtechnique has enormous potential as a feature extractor and is one of theapproaches to improve the reliability of the recognition systems. PCA is hugelyutilized in all forms of scrutiny because it is a simple method.
It likewiselessens the dimension of a figure i.e. from higher dimension to lower dimensionspace effectively and yet holds the primary information of the images. In this technique,every image in the training phase are represented as weighted eigenvectors thatare linearly combined and known as “Eigenfaces” and these eigenvectors areobtained from the covariance grid of a training dataset which is known as basisfunction. From the largely appropriate Eigenfaces the weights of an image areobtained. Similarity between the pixels among images in a dataset bymeans of their covariance matrix is one of the advantages taken by Eigen faces.Byprojecting the test image on the subspace spanned by the eigenfaces therecognition of the Soil expression is performed and then the furtherclassification is carried out by a distance measure method known as Euclideandistance. Following are the steps involved to recognise the Soilexpressions using PCA approach: 1 Collection of Images to make the Database.
Firstly theimages of various area of soil captured using digital camera with requiredresolution for better quality or by scanner. The construction of database isclearly dependent on application. All the databases are collected and stored ina folder. 2 Checking whether Image is colored or gray: Initially thesoil image is taken and is checked whether it is colored or gray image by usingthe command size. If the soil image taken is colored then it is converted togray image to make it two dimensional (m x n). After this the class type ofgray image is checked to make sure the image type is doubled or not. If it isnot doubled than convert the image to double. 3 Mean and Standard Deviation of Images is Calculated: Afterthis the image is converted into a column vector of dimension mxn, so that atypical image of size 112×92 for example becomes a vector of dimension 10304,denoted as T.
Now the mean of the image is calculated by using equation (4) andstandard deviation (S) is calculated using equation(13).Also the standard deviation (ustd) and mean (um) is setpractically approximately close to mean and standard deviation calculatedabove. 4 Normalization: Next normalization of images is doneusing equation (14) in order to make all images of uniform dimension. 5 Calculating Train Centred Images: Subtracting the meanfrom column vector matrix of training images in order to obtain the centredimages. 6 Calculating Eigen Vectors and Values from the covariancematrix.
7 Creating Eigen faces: Eigen Vectors obtained after SVDare sorted in descending order and the top Eigen vectors are considered asEigen Faces. 8 Calculating Train Weights: Now the weights aredetermined by calculating the dot product of transpose of Eigen Faces matrixand Train Centred Images. 9 Store Train Weights in Sink for Further Comparison: Theabove mentioned procedure from step (2 to 8) is applied on each train image andfinally one by one train weights are stored in sink for further comparison. 10 Euclidean distance Classifier: In this block firstly allsteps from (2 to 7) are applied on the test image to compute its test weightsand then the difference between this test weights and the train weights storedin the sink. 11 FaceRecognized: Finally the minimum distance gives the best match or can be saidsimilar soil pH Identified.