diff --git a/chapters/5-Discussion.tex b/chapters/5-Discussion.tex
index b1e9d6f2c06791c3e520834d47f881759f0e6533..ba3571ffe428f1ac33882a41cc8e209422bf2928 100644
--- a/chapters/5-Discussion.tex
+++ b/chapters/5-Discussion.tex
@@ -1 +1,45 @@
-\chapter{Discussion}
\ No newline at end of file
+\chapter{Discussion}
+
+\section{Interpretation of the Results}
+
+The benchmark results reveal clear performance differentials among the evaluated libraries. In particular, the image conversion tests showed that alternatives such as OpenCvSharp combined with SkiaSharp, and Emgu CV paired with Structure.Sketching, drastically reduce conversion times compared to ImageSharp. For example, while ImageSharp required 2754 ms for image conversion, the Emgu CV + Structure.Sketching combination achieved the task in just 490 ms. Similarly, pixel iteration tests indicated that Emgu CV yielded an average iteration time close to that of ImageSharp but with a significant advantage in cost, despite slightly higher memory usage.
+
+These results mean that for core operations—loading an image, converting formats, and iterating through pixels—there are measurable improvements in speed and efficiency when using alternative libraries. The reduced processing times translate directly into enhanced responsiveness for applications that rely on image processing, making them highly relevant for performance-critical systems.
+
+\section{Conclusions and Comparative Strengths}
+
+The evidence leads to several key conclusions:
+\begin{itemize}
+    \item \textbf{No Universally Best Library:} There is no single library that outperforms others across every metric. Each alternative presents a distinct balance of speed, memory consumption, integration effort, and cost.
+    \item \textbf{Emgu CV Strengths and Weaknesses:} Emgu CV excels in handling complex image processing tasks, particularly in pixel iteration, where it achieved one of the fastest mean times. Its performance advantage is balanced by higher memory usage during intensive operations. Moreover, its cost-effective licensing (a one-time fee versus ImageSharp’s recurring cost) makes it appealing for long-term applications.
+    \item \textbf{SkiaSharp Strengths and Weaknesses:} SkiaSharp demonstrates superior performance in image conversion tasks, with very low memory allocation and rapid processing times. However, its pixel manipulation capabilities are more basic compared to those of Emgu CV, suggesting it is best suited as a complement to another library that handles more intensive processing.
+    \item \textbf{Alternative Combinations:} The combination of Emgu CV and SkiaSharp appears to provide the best overall trade-off. Emgu CV covers the low-level, performance-critical aspects of image processing, while SkiaSharp offers robust, high-quality 2D rendering and efficient format conversion.
+\end{itemize}
+
+These conclusions confirm that while no library is universally optimal, the right combination can cover a broader range of requirements while addressing specific weaknesses inherent in any single solution.
+
+\section{Relevance to the Larger Field}
+
+The findings are relevant not only to the specific context of replacing ImageSharp in commercial applications but also to the broader domain of cost-effective and efficient image processing. In an era where performance and cost savings are critical—especially for web services, mobile apps, and enterprise solutions—the ability to reduce licensing fees without sacrificing processing speed is of significant importance. Furthermore, these results contribute to ongoing discussions in the image processing community about the trade-offs between open-source alternatives and commercial solutions.
+
+\section{Implications for Further Research, Theory, and Practice}
+
+\subsection{Implications for Practice}
+\begin{itemize}
+    \item \textbf{Adoption of Hybrid Solutions:} Practitioners can benefit from a hybrid approach —using Emgu CV for intensive processing and SkiaSharp for rendering— to optimize performance and cost.
+    \item \textbf{Cost Savings:} The significant reduction in recurring expenses (as compared to ImageSharp) can free up resources for other critical development activities.
+\end{itemize}
+
+\subsection{Implications for Further Research}
+\begin{itemize}
+    \item \textbf{Extended Benchmarking:} Future studies could expand the benchmarking metrics to include additional operations such as asynchronous processing, multi-threading, and GPU acceleration. Evaluating real-world workload scenarios would also help refine the performance comparisons.
+    \item \textbf{Integration Complexity:} Investigating the ease of integration and maintainability over long-term projects would provide further insights into the practical challenges of deploying these libraries in diverse environments.
+    \item \textbf{User-Centered Evaluations:} Beyond raw performance metrics, future research might consider end-user impact, including subjective assessments of responsiveness and quality, to complement the quantitative analysis.
+\end{itemize}
+
+\subsection{Methodological Considerations}
+The approach chosen for this study—focusing on image conversion and pixel iteration metrics—proved effective for isolating core performance aspects. However, incorporating a broader set of benchmarks (such as memory overhead in multi-threaded contexts or performance under varying image resolutions) would provide a more comprehensive view of each library's capabilities. Additionally, further studies could consider the evolution of these libraries over time, as continuous improvements may shift the balance of strengths and weaknesses.
+
+\section{Summary of the Discussion}
+
+In summary, the results indicate that while no single library is perfect, the combination of Emgu CV and SkiaSharp offers a compelling alternative to ImageSharp by delivering superior performance and cost advantages. The strengths of each library complement one another, and the findings have broad implications for cost-sensitive, performance-critical image processing applications. Future research can build upon this work by exploring additional metrics, integration challenges, and user experience factors, further refining our understanding of how to best meet the diverse needs of modern image processing tasks.