feat: add flowchart representation of image prediction process and enhance README with flowchart and multi-model consensus methods overview

FLOW.gv

@@ -0,0 +1,66 @@
+digraph ImagePredictionFlow {
+    graph [fontname="Arial", fontsize="10", rankdir="TB"]; // Top-to-Bottom, Reduced Width
+    node [shape="rect", style="rounded,filled", fontname="Arial", fontsize="10", fillcolor="lightblue", gradientangle="90"];
+    edge [fontname="Arial", fontsize="8"];
+
+    A [label="User Upload,\nPredict", fillcolor="lightgreen"]; //Shorter Label
+    B [label="Img Pre-proc,\nAgent Init", fillcolor="lightyellow"];
+
+    subgraph cluster_models {
+        label = "Model Ensemble";
+        style = "dashed";
+
+        ImageIn [shape=point, label="", width=0, height=0];
+        Model1 [label="Model1", fillcolor="lightcoral"];   //Shorter Labels
+        Model2 [label="Model2", fillcolor="lightcoral"];
+        Model3 [label="Model3", fillcolor="lightcoral"];
+        Model4 [label="Model4", fillcolor="lightcoral"];
+        Model5 [label="Model5", fillcolor="lightcoral"];
+        Model6 [label="Model6", fillcolor="lightcoral"];
+        Model7 [label="Model7", fillcolor="lightcoral"];
+        WeightedConsensusInput [label="Model Results", fillcolor="lightyellow"];  //Shorter Label
+
+        ImageIn -> Model1;  ImageIn -> Model2;  ImageIn -> Model3;  ImageIn -> Model4;  ImageIn -> Model5;  ImageIn -> Model6;  ImageIn -> Model7;
+        Model1 -> WeightedConsensusInput;  Model2 -> WeightedConsensusInput; Model3 -> WeightedConsensusInput; Model4 -> WeightedConsensusInput; Model5 -> WeightedConsensusInput; Model6 -> WeightedConsensusInput; Model7 -> WeightedConsensusInput;
+    }
+
+    ContextualIntelligenceAgent [label="Contextual\nIntelligence Agent", fillcolor="lightcyan"]; //Shorter Label
+    BaggingAgent [label="BaggingAgent", fillcolor="lightcyan"];        //Shorter Label
+    DeepEnsembleAgent [label="DeepEnsemble\nAgent", fillcolor="lightcyan"];        //Shorter Label
+    EvolutionEnsembleAgent [label="EvolutionEnsemble\nAgent", fillcolor="lightcyan"];       //Shorter Label
+
+    WeightManager [label="Weight\nManager", fillcolor="lightcyan"];    //Shorter Label
+    WeightedConsensus [label="Weighted\nConsensus", fillcolor="lightgreen"];
+    OptimizeAgent [label="Weight\nOpt Agent", fillcolor="lightcyan"];        //Shorter Label
+
+
+    subgraph cluster_forensics {
+        label = "Forensic Analysis";
+        style = "dashed";
+
+        ForensicIn [shape=point, label="", width=0, height=0];
+        GradientProcessing [label="Gradient\nProcessing", fillcolor="lightpink"];      //Shorter Labels
+        MinMaxProcessing [label="MinMax\nProcessing", fillcolor="lightpink"];
+        ELAPorcessing [label="ELAPorcessing", fillcolor="lightpink"];
+        BitPlaneExtraction [label="BitPlane\nExtraction", fillcolor="lightpink"];
+        WaveletBasedNoiseAnalysis [label="Wavelet\nNoise Analysis", fillcolor="lightpink"];
+        AnomalyAgent [label="Anomaly\nDetection", fillcolor="lightcyan"];        //Shorter Label
+
+        ForensicIn -> GradientProcessing;  ForensicIn -> MinMaxProcessing;  ForensicIn -> ELAPorcessing;  ForensicIn -> BitPlaneExtraction;  ForensicIn -> WaveletBasedNoiseAnalysis;
+        GradientProcessing -> AnomalyAgent;  MinMaxProcessing -> AnomalyAgent;  ELAPorcessing -> AnomalyAgent;  BitPlaneExtraction -> AnomalyAgent;  WaveletBasedNoiseAnalysis -> AnomalyAgent;
+    }
+
+    DataLoggingAndOutput [label="Data Logging\nOutput", fillcolor="lightsalmon"];//Shorter Label
+    ResultsDisplay [label="Results", fillcolor="lightgreen"];    //Shorter Label
+
+    // Connections
+    A -> B;
+    B -> ImageIn;
+
+    WeightedConsensusInput -> ContextualIntelligenceAgent;  WeightedConsensusInput -> BaggingAgent;  WeightedConsensusInput -> DeepEnsembleAgent;  WeightedConsensusInput -> EvolutionEnsembleAgent;  // Connect agents
+    ContextualIntelligenceAgent -> WeightManager;  BaggingAgent -> WeightManager;  DeepEnsembleAgent -> WeightManager;  EvolutionEnsembleAgent -> WeightManager;      //  Agents to WM
+    WeightManager -> WeightedConsensus;
+    WeightedConsensus -> OptimizeAgent;  OptimizeAgent -> WeightManager;
+    WeightedConsensus -> ForensicIn;  AnomalyAgent -> DataLoggingAndOutput;
+    DataLoggingAndOutput -> ResultsDisplay;
+}

README.md

@@ -219,6 +219,10 @@ When you upload an image for analysis and click the "Predict" button, the follow
 *   **Data Type Conversion**: Numerical values (like AI Score, Real Score) are converted to standard Python floats to ensure proper JSON serialization.
 
 ---
+## Flow-Chart
+
+<img src="graph_alt.svg">
+
 
 ## Roadmap & Features
 
@@ -334,3 +338,22 @@ Here's the updated table with an additional column providing **instructions on h
 
 ---
 
+---
+### **Overview of Multi-Model Consensus Methods in ML**
+| **Method**               | **Category**               | **Description**                                  | **Key Advantages**                                | **Key Limitations**                                          | **Weaknesses**                          | **Strengths**                                                                 |
+|--------------------------|----------------------------|--------------------------------------------------|---------------------------------------------------|--------------------------------------------------------------|----------------------------------------|--------------------------------------------------------------------------------|
+| **Bagging (e.g., Random Forest)** | **Traditional Ensembles**  | Trains multiple models on bootstrapped data subsets, aggregating predictions | Reduces overfitting (~variance reduction)           | Computationally costly for large datasets; models can be correlated | Not robust to adversarial attacks      | Simple to implement; robust to noisy data; handles high-dimensional data well     |
+| **Boosting (e.g., XGBoost, LightGBM)** | **Traditional Ensembles**  | Iteratively corrects errors using weighted models | High accuracy on structured/tabular data           | Risk of overfitting; sensitive to noisy data                   | Computationally intensive              | Dominates in competitions (e.g., Kaggle); scalable for medium datasets           |
+| **Stacking**             | **Traditional Ensembles**  | Combines predictions via a meta-learner          | Can outperform individual models; flexible          | Increased complexity and data leakage risk                   | Requires careful hyperparameter tuning | Excels in combining diverse models (e.g., trees + SVMs + linear models)            |
+| **Deep Ensembles**       | **Deep Learning Ensembles**| Multiple independently trained neural networks   | Uncertainty estimation; robust to data shifts        | High computational cost; memory-heavy                        | Model coordination challenges          | State-of-the-art in safety-critical domains (e.g., medical imaging, autonomous vehicles) |
+| **Snapshot Ensembles**   | **Deep Learning Ensembles**| Saves models at different optimization stages    | Efficient (only one training run)                   | Limited diversity (same architecture/init)                   | Requires careful checkpoint selection  | Lightweight for tasks like on-device deployment                                  |
+| **Monte Carlo Dropout**  | **Approximate Ensembles**  | Applies dropout at inference to simulate many models | Free ensemble (during testing)                      | Approximates uncertainty poorly compared to deep ensembles    | Limited diversity                     | Cheap and simple; useful for quick uncertainty estimates                         |
+| **Mixture of Experts (MoE)** | **Scalable Ensembles**  | Specialized sub-models (experts) with a gating mechanism | Efficient scaling (only activate sub-models)        | Training instability; uneven expert utilization              | Requires expert/gate orchestration     | Dominates large-scale applications like Switch Transformers and Hyper-Cloud systems |
+| **Bayesian Neural Networks (BNNs)** | **Probabilistic Ensembles** | Models weights as probability distributions      | Built-in uncertainty quantification                 | Intractable to train exactly; approximations needed            | Difficult optimization                | Essential for risk-averse applications (robotics, finance)                       |
+| **Ensemble Knowledge Distillation** | **Model Compression**   | Trains a single model to mimic an ensemble       | Reduces compute/memory demands                   | Loses some ensemble benefits (diversity, uncertainty)         | Relies on a high-quality teacher ensemble | Enables deployment of ensemble-like performance in compact models (edge devices) |
+| **Noisy Student Training** | **Semi-Supervised Ensembles** | Iterative self-training with teacher-student loops | Uses unlabeled data effectively; improves robustness| Needs large unlabeled data and computational resources         | Vulnerable to error propagation         | State-of-the-art in semi-supervised settings (e.g., NLP)                         |
+| **Evolutionary Ensembles** | **Dynamic Ensembles**    | Uses genetic algorithms to evolve model populations | Adaptive diversity generation                      | High time/cost for evolution; niche use cases                 | Hard to interpret                     | Useful for non-stationary environments/on datasets with drift                  |
+| **Consensus Networks**   | **NLP/Serverless Ensembles** | Distributes models across clients/aggregates votes | Decentralized privacy-preserving predictions     | Communication overhead; non-i.i.d. data conflicts       | Requires synchronized coordination    | Fed into federated learning systems (e.g., healthcare, finance)                 |
+| **Hybrid Systems**       | **Cross-Architecture Ensembles** | Combines models (e.g., CNNs, GNNs, transformers) | Captures multi-modal or heterogeneous patterns     | Integration complexity; delayed inference               | Model conflicts                       | Dominates in tasks requiring domain-specific reasoning (e.g., drug discovery)  |
+| **Self-Supervised Ensembles** | **Vision/NLP**          | Uses contrastive learning with multiple models (e.g., MoCo, SimCLR) | Data-efficient; strong performance on downstream tasks | Training is resource-heavy; requires pre-training at scale | Low interpretability                  | Foundations for modern vision/NLP architectures (e.g., resists data scarcity)   |
+---